Tag Archives: Machine Perception

Toward Generalized Sim-to-Real Transfer for Robot Learning

Reinforcement and imitation learning methods in robotics research can enable autonomous environmental navigation and efficient object manipulation, which in turn opens up a breadth of useful real-life applications. Previous work has demonstrated how robots that learn end-to-end using deep neural networks can reliably and safely interact with the unstructured world around us by comprehending camera observations to take actions and solve tasks. However, while end-to-end learning methods can generalize and scale for complicated robot manipulation tasks, they require hundreds of thousands real world robot training episodes, which can be difficult to obtain. One can attempt to alleviate this constraint by using a simulation of the environment that allows virtual robots to learn more quickly and at scale, but the simulations’ inability to exactly match the real world presents a challenge c ommonly referred to as the sim-to-real gap. One important source of the gap comes from discrepancies between the images rendered in simulation and the real robot camera observations, which then causes the robot to perform poorly in the real world.

To-date, work on bridging this gap has employed a technique called pixel-level domain adaptation, which translates synthetic images to realistic ones at the pixel level. One example of this technique is GraspGAN, which employs a generative adversarial network (GAN), a framework that has been very effective at image generation, to model this transformation between simulated and real images given datasets of each domain. These pseudo-real images correct some sim-to-real gap, so policies learned with simulation execute more successfully on real robots. A limitation for their use in sim-to-real transfer, however, is that because GANs translate images at the pixel-level, multi-pixel features or structures that are necessary for robot task learning may be arbitrarily modified or even removed.

To address the above limitation, and in collaboration with the Everyday Robot Project at X, we introduce two works, RL-CycleGAN and RetinaGAN, that train GANs with robot-specific consistencies — so that they do not arbitrarily modify visual features that are specifically necessary for robot task learning — and thus bridge the visual discrepancy between sim and real. We demonstrate how these consistencies preserve features critical to policy learning, eliminating the need for hand-engineered, task-specific tuning, which in turn allows for this sim-to-real methodology to work flexibly across tasks, domains, and learning algorithms. With RL-CycleGAN, we describe our sim-to-real transfer methodology and demonstrate state-of-the-art performance on real world grasping tasks trained with RL. With RetinaGAN, we extend our approach to include imitation learning with a door opening task.

RL-CycleGAN
In “RL-CycleGAN: Reinforcement Learning Aware Simulation-To-Real”, we leverage a variation of CycleGAN for sim-to-real adaptation by ensuring consistency of task-relevant features between real and simulated images. CycleGAN encourages preservation of image contents by ensuring an adapted image transformed back to the original domain is identical to the original image, which is called cycle consistency. To further encourage the adapted images to be useful for robotics, the CycleGAN is jointly trained with a reinforcement learning (RL) robot agent that ensures the robot’s actions are the same given both the original images and those after GAN-adaptation. That is, task-specific features like robot arm or graspable object locations are unaltered, but the GAN may still alter lighting or textural differences between domains that do not affect task-level decisions.

Evaluating RL-CycleGAN
We evaluated RL-CycleGAN on a robotic indiscriminate grasping task. Trained on 580,000 real trials and simulations adapted with RL-CycleGAN, the robot grasps objects with 94% success, surpassing the 89% success rate of the prior state-of-the-art sim-to-real method GraspGAN and the 87% mark using real-only data without simulation. With only 28,000 trials, the RL-CycleGAN method reaches 86%, comparable to the previous baselines with 20x the data. Some examples of the RL-CycleGAN output alongside the simulation images are shown below.

Comparison between simulation images of robot grasping before (left) and after RL-CycleGAN translation (right).

RetinaGAN
While RL-CycleGAN reliably transfers from sim-to-real for the RL domain using task awareness, a natural question arises: can we develop a more flexible sim-to-real transfer technique that applies broadly to different tasks and robot learning techniques?

In “RetinaGAN: An Object-Aware Approach to Sim-to-Real Transfer”, presented at ICRA 2021, we develop such a task-decoupled, algorithm-decoupled GAN approach to sim-to-real transfer by instead focusing on robots’ perception of objects. RetinaGAN enforces strong object-semantic awareness through perception consistency via object detection to predict bounding box locations for all objects on all images. In an ideal sim-to-real model, we expect the object detector to predict the same box locations before and after GAN translation, as objects should not change structurally. RetinaGAN is trained toward this ideal by backpropagation, such that there is consistency in perception of objects both when a) simulated images are transformed from simulation to real and then back to simulation and b) when real images are transformed from real to simulation and then back to real. We find this object-based consistency to be more widely applicable than the task-specific consistency required by RL-CycleGAN.

Diagram of RetinaGAN stages. The simulated image (top left) is transformed by the sim-to-real generator and subsequently by the real-to-sim generator. The real image (bottom left) undergoes the transformation in reverse order. Having separate pipelines that start with the simulated and real images improves the GAN’s performance.

Evaluating RetinaGAN on a Real Robot
Given the goal of building a more flexible sim-to-real transfer technique, we evaluate RetinaGAN in multiple ways to understand for which tasks and under what conditions it accomplishes sim-to-real transfer.

We first apply RetinaGAN to a grasping task. As demonstrated visually below, RetinaGAN emphasizes the translation of realistic object textures, shadows, and lighting, while maintaining the visual quality and saliency of the graspable objects. We couple a pre-trained RetinaGAN model with the distributed reinforcement learning method Q2-Opt to train a vision-based task model for instance grasping. On real robots, this policy grasps object instances with 80% success when trained on a hundred thousand episodes — outperforming prior adaptation methods RL-CycleGAN and CycleGAN (both achieving ~68%) and training without domain adaptation (grey bars below: 19% with sim data, 22% with real data, and 54% with mixed data). This gives us confidence that perception consistency is a valuable strategy for sim-to-real transfer. Further, with just 10,000 training episodes (8% of the data), the RL policy with RetinaGAN grasps with 66% success, demonstrating performance of prior methods with significantly less data.

Evaluation performance of RL policies on instance grasping, trained with various datasets and sim-to-real methods. Low-Data RetinaGAN uses 8% of the real dataset.
The simulated grasping environment (left) is translated to a realistic image (right) using RetinaGAN.

Next, we pair RetinaGAN with a different learning method, behavioral cloning, to open conference room doors given demonstrations by human operators. Using images from both simulated and real demonstrations, we train RetinaGAN to translate the synthetic images to look realistic, bridging the sim-to-real gap. We then train a behavior cloning model to imitate the task-solving actions of the human operators within real and RetinaGAN-adapted sim demonstrations. When evaluating this model by predicting actions to take, the robot enters real conference rooms over 93% of the time, surpassing baselines of 75% and below.

Both of the above images show the same simulation, but RetinaGAN translates simulated door opening images (left) to look more like real robot sensor data (right).
Three examples of the real robot successfully opening conference room doors using the RetinaGAN-trained behavior cloning policy.

Conclusion
This work has demonstrated how additional constraints on GANs may address the visual sim-to-real gap without requiring task-specific tuning; these approaches reach higher real robot success rates with less data collection. RL-CycleGAN translates synthetic images to realistic ones with an RL-consistency loss that automatically preserves task-relevant features. RetinaGAN is an object-aware sim-to-real adaptation technique that transfers robustly across environments and tasks, agnostic to the task learning method. Since RetinaGAN is not trained with any task-specific knowledge, we show how it can be reused for a novel object pushing task. We hope that work on the sim-to-real gap further generalizes toward solving task-agnostic robotic manipulation in unstructured environments.

Acknowledgements
Research into RL-CycleGAN was conducted by Kanishka Rao, Chris Harris, Alex Irpan, Sergey Levine, Julian Ibarz, and Mohi Khansari. Research into RetinaGAN was conducted by Daniel Ho, Kanishka Rao, Zhuo Xu, Eric Jang, Mohi Khansari, and Yunfei Bai. We’d also like to give special thanks to Ivonne Fajardo, Noah Brown, Benjamin Swanson, Christopher Paguyo, Armando Fuentes, and Sphurti More for overseeing the robot operations. We thank Paul Wohlhart, Konstantinos Bousmalis, Daniel Kappler, Alexander Herzog, Anthony Brohan, Yao Lu, Chad Richards, Vincent Vanhoucke, and Mrinal Kalakrishnan, Max Braun and others in the Robotics at Google team and the Everyday Robot Project for valuable discussions and help.

Source: Google AI Blog


Project Guideline: Enabling Those with Low Vision to Run Independently

For the 285 million people around the world living with blindness or low vision, exercising independently can be challenging. Earlier this year, we announced Project Guideline, an early-stage research project, developed in partnership with Guiding Eyes for the Blind, that uses machine learning to guide runners through a variety of environments that have been marked with a painted line. Using only a phone running Guideline technology and a pair of headphones, Guiding Eyes for the Blind CEO Thomas Panek was able to run independently for the first time in decades and complete an unassisted 5K in New York City’s Central Park.

Safely and reliably guiding a blind runner in unpredictable environments requires addressing a number of challenges. Here, we will walk through the technology behind Guideline and the process by which we were able to create an on-device machine learning model that could guide Thomas on an independent outdoor run. The project is still very much under development, but we’re hopeful it can help explore how on-device technology delivered by a mobile phone can provide reliable, enhanced mobility and orientation experiences for those who are blind or low vision.

Thomas Panek using Guideline technology to run independently outdoors.

Project Guideline
The Guideline system consists of a mobile device worn around the user’s waist with a custom belt and harness, a guideline on the running path marked with paint or tape, and bone conduction headphones. Core to the Guideline technology is an on-device segmentation model that takes frames from a mobile device’s camera as input and classifies every pixel in the frame into two classes, “guideline” and “not guideline”. This simple confidence mask, applied to every frame, allows the Guideline app to predict where runners are with respect to a line on the path, without using location data. Based on this prediction and the proceeding smoothing/filtering function, the app sends audio signals to the runners to help them orient and stay on the line, or audio alerts to tell runners to stop if they veer too far away.

Project Guideline uses Android’s built-in Camera 2 and MLKit APIs and adds custom modules to segment the guideline, detect its position and orientation, filter false signals, and send a stereo audio signal to the user in real-time.

We faced a number of important challenges in building the preliminary Guideline system:

  1. System accuracy: Mobility for the blind and low vision community is a challenge in which user safety is of paramount importance. It demands a machine learning model that is capable of generating accurate and generalized segmentation results to ensure the safety of the runner in different locations and under various environmental conditions.
  2. System performance: In addition to addressing user safety, the system needs to be performative, efficient, and reliable. It must process at least 15 frames per second (FPS) in order to provide real-time feedback for the runner. It must also be able to run for at least 3 hours without draining the phone battery, and must work offline, without the need for internet connection should the walking/running path be in an area without data service.
  3. Lack of in-domain data: In order to train the segmentation model, we needed a large volume of video consisting of roads and running paths that have a yellow line on them. To generalize the model, data variety is equally as critical as data quantity, requiring video frames taken at different times of day, with different lighting conditions, under different weather conditions, at different locations, etc.

Below, we introduce solutions for each of these challenges.

Network Architecture
To meet the latency and power requirements, we built the line segmentation model on the DeepLabv3 framework, utilizing MobilenetV3-Small as the backbone, while simplifying the outputs to two classes – guideline and background.

The model takes an RGB frame and generates an output grayscale mask, representing the confidence of each pixel’s prediction.

To increase throughput speed, we downsize the camera feed from 1920 x 1080 pixels to 513 x 513 pixels as input to the DeepLab segmentation model. To further speed-up the DeepLab model for use on mobile devices, we skipped the last up-sample layer, and directly output the 65 x 65 pixel predicted masks. These 65 x 65 pixel predicted masks are provided as input to the post processing. By minimizing the input resolution in both stages, we’re able to improve the runtime of the segmentation model and speed up post-processing.

Data Collection
To train the model, we required a large set of training images in the target domain that exhibited a variety of path conditions. Not surprisingly, the publicly available datasets were for autonomous driving use cases, with roof mounted cameras and cars driving between the lines, and were not in the target domain. We found that training models on these datasets delivered unsatisfying results due to the large domain gap. Instead, the Guideline model needed data collected with cameras worn around a person’s waist, running on top of the line, without the adversarial objects found on highways and crowded city streets.

The large domain gap between autonomous driving datasets and the target domain. Images on the left courtesy of the Berkeley DeepDrive dataset.

With preexisting open-source datasets proving unhelpful for our use case, we created our own training dataset composed of the following:

  1. Hand-collected data: Team members temporarily placed guidelines on paved pathways using duct tape in bright colors and recorded themselves running on and around the lines at different times of the day and in different weather conditions.
  2. Synthetic data: The data capture efforts were complicated and severely limited due to COVID-19 restrictions. This led us to build a custom rendering pipeline to synthesize tens of thousands of images, varying the environment, weather, lighting, shadows, and adversarial objects. When the model struggled with certain conditions in real-world testing, we were able to generate specific synthetic datasets to address the situation. For example, the model originally struggled with segmenting the guideline amidst piles of fallen autumn leaves. With additional synthetic training data, we were able to correct for that in subsequent model releases.
Rendering pipeline generates synthetic images to capture a broad spectrum of environments.

We also created a small regression dataset, which consisted of annotated samples of the most frequently seen scenarios combined with the most challenging scenarios, including tree and human shadows, fallen leaves, adversarial road markings, sunlight reflecting off the guideline, sharp turns, steep slopes, etc. We used this dataset to compare new models to previous ones and to make sure that an overall improvement in accuracy of the new model did not hide a reduction in accuracy in particularly important or challenging scenarios.

Training Procedure
We designed a three-stage training procedure and used transfer learning to overcome the limited in-domain training dataset problem. We started with a model that was pre-trained on Cityscape, and then trained the model using the synthetic images, as this dataset is larger but of lower quality. Finally, we fine-tuned the model using the limited in-domain data we collected.

Three-stage training procedure to overcome the limited data issue. Images in the left column courtesy of Cityscapes.

Early in development, it became clear that the segmentation model's performance suffered at the top of the image frame. As the guidelines travel further away from the camera’s point of view at the top of the frame, the lines themselves start to vanish. This causes the predicted masks to be less accurate at the top parts of the frame. To address this problem, we computed a loss value that was based on the top k pixel rows in every frame. We used this value to select those frames that included the vanishing guidelines with which the model struggled, and trained the model repeatedly on those frames. This process proved to be very helpful not only in addressing the vanishing line problem, but also for solving other problems we encountered, such as blurry frames, curved lines and line occlusion by adversarial objects.

The segmentation model’s accuracy and robustness continuously improved even in challenging cases.

System Performance
Together with Tensorflow Lite and ML Kit, the end-to-end system runs remarkably fast on Pixel devices, achieving 29+ FPS on Pixel 4 XL and 20+ FPS on Pixel 5. We deployed the segmentation model entirely on DSP, running at 6 ms on Pixel 4 XL and 12 ms on Pixel 5 with high accuracy. The end-to-end system achieves 99.5% frame success rate, 93% mIoU on our evaluation dataset, and passes our regression test. These model performance metrics are incredibly important and enable the system to provide real-time feedback to the user.

What's Next
We’re still at the beginning of our exploration, but we’re excited about our progress and what’s to come. We’re starting to collaborate with additional leading non-profit organizations that serve the blind and low vision communities to put more Guidelines in parks, schools, and public places. By painting more lines, getting direct feedback from users, and collecting more data under a wider variety of conditions, we hope to further generalize our segmentation model and improve the existing feature-set. At the same time, we are investigating new research and techniques, as well as new features and capabilities that would improve the overall system robustness and reliability.

To learn more about the project and how it came to be, read Thomas Panek’s story. If you want to help us put more Guidelines in the world, please visit goo.gle/ProjectGuideline.

Acknowledgements
Project Guideline is a collaboration across Google Research, Google Creative Lab, and the Accessibility Team. We especially would like to thank our team members: Mikhail Sirotenko, Sagar Waghmare, Lucian Lonita, Tomer Meron, Hartwig Adam, Ryan Burke, Dror Ayalon, Amit Pitaru, Matt Hall, John Watkinson, Phil Bayer, John Mernacaj, Cliff Lungaretti, Dorian Douglass, Kyndra LoCoco. We also thank Fangting Xia, Jack Sim and our other colleagues and friends from the Mobile Vision team and Guiding Eyes for the Blind.

Source: Google AI Blog


ALIGN: Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision

Learning good visual and vision-language representations is critical to solving computer vision problems — image retrieval, image classification, video understanding — and can enable the development of tools and products that change people’s daily lives. For example, a good vision-language matching model can help users find the most relevant images given a text description or an image input and help tools such as Google Lens find more fine-grained information about an image.

To learn such representations, current state-of-the-art (SotA) visual and vision-language models rely heavily on curated training datasets that require expert knowledge and extensive labels. For vision applications, representations are mostly learned on large-scale datasets with explicit class labels, such as ImageNet, OpenImages, and JFT-300M. For vision-language applications, popular pre-training datasets, such as Conceptual Captions and Visual Genome Dense Captions, all require non-trivial data collection and cleaning steps, limiting the size of datasets and thus hindering the scale of the trained models. In contrast, natural language processing (NLP) models have achieved SotA performance on GLUE and SuperGLUE benchmarks by utilizing large-scale pre-training on raw text without human labels.

In "Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision", to appear at ICML 2021, we propose bridging this gap with publicly available image alt-text data (written copy that appears in place of an image on a webpage if the image fails to load on a user's screen) in order to train larger, state-of-the-art vision and vision-language models. To that end, we leverage a noisy dataset of over one billion image and alt-text pairs, obtained without expensive filtering or post-processing steps in the Conceptual Captions dataset. We show that the scale of our corpus can make up for noisy data and leads to SotA representation, and achieves strong performance when transferred to classification tasks such as ImageNet and VTAB. The aligned visual and language representations also set new SotA results on Flickr30K and MS-COCO benchmarks, even when compared with more sophisticated cross-attention models, and enable zero-shot image classification and cross-modality search with complex text and text + image queries.

Creating the Dataset
Alt-texts usually provide a description of what the image is about, but the dataset is “noisy” because some text may be partly or wholly unrelated to its paired image.

Example image-text pairs randomly sampled from the training dataset of ALIGN. One clearly noisy text label is marked in italics.

In this work, we follow the methodology of constructing the Conceptual Captions dataset to get a version of raw English alt-text data (image and alt-text pairs). While the Conceptual Captions dataset was cleaned by heavy filtering and post-processing, this work scales up visual and vision-language representation learning by relaxing most of the cleaning steps in the original work. Instead, we only apply minimal frequency-based filtering. The result is a much larger but noisier dataset of 1.8B image-text pairs.

ALIGN: A Large-scale ImaGe and Noisy-Text Embedding
For the purpose of building larger and more powerful models easily, we employ a simple dual-encoder architecture that learns to align visual and language representations of the image and text pairs. Image and text encoders are learned via a contrastive loss (formulated as normalized softmax) that pushes the embeddings of matched image-text pairs together while pushing those of non-matched image-text pairs (within the same batch) apart. The large-scale dataset makes it possible for us to scale up the model size to be as large as EfficientNet-L2 (image encoder) and BERT-large (text encoder) trained from scratch. The learned representation can be used for downstream visual and vision-language tasks.

Figure of ImageNet credit to (Krizhevsky et al. 2012) and VTAB figure credit to (Zhai et al. 2019)

The resulting representation can be used for vision-only or vision-language task transfer. Without any fine-tuning, ALIGN powers cross-modal search – image-to-text search, text-to-image search, and even search with joint image+text queries, examples below.

Evaluating Retrieval and Representation
The learned ALIGN model with BERT-Large and EfficientNet-L2 as text and image encoder backbones achieves SotA performance on multiple image-text retrieval tasks (Flickr30K and MS-COCO) in both zero-shot and fine-tuned settings, as shown below.

Flickr30K (1K test set) [email protected] MS-COCO (5K test set) [email protected]
Setting Model    image → text       text → image       image → text       text → image   
Zero-shot ImageBERT    70.7 54.3 44.0 32.3
UNITER 83.6 68.7 - -
CLIP 88.0 68.7 58.4 37.8
ALIGN 88.6 75.7 58.6 45.6
Fine-tuned    GPO 88.7 76.1 68.1 52.7
UNITER 87.3 75.6 65.7 52.9
ERNIE-ViL 88.1 76.7 - -
VILLA 87.9 76.3 - -
Oscar - - 73.5 57.5
ALIGN 95.3 84.9 77.0 59.9
Image-text retrieval results ([email protected]) on Flickr30K and MS-COCO datasets (both zero-shot and fine-tuned). ALIGN significantly outperforms existing methods including the cross-modality attention models that are too expensive for large-scale retrieval applications.

ALIGN is also a strong image representation model. Shown below, with frozen features, ALIGN slightly outperforms CLIP and achieves a SotA result of 85.5% top-1 accuracy on ImageNet. With fine-tuning, ALIGN achieves higher accuracy than most generalist models, such as BiT and ViT, and is only worse than Meta Pseudo Labels, which requires deeper interaction between ImageNet training and large-scale unlabeled data.

Model (backbone)    [email protected] w/ frozen features       [email protected]1       [email protected]   
WSL (ResNeXt-101 32x48d) 83.6 85.4 97.6
CLIP (ViT-L/14) 85.4 - -
BiT (ResNet152 x 4) - 87.54 98.46
NoisyStudent (EfficientNet-L2) - 88.4 98.7
ViT (ViT-H/14) - 88.55 -
Meta-Pseudo-Labels (EfficientNet-L2)    - 90.2 98.8
ALIGN (EfficientNet-L2) 85.5 88.64 98.67
ImageNet classification results comparison with supervised training (fine-tuning).

Zero-Shot Image Classification
Traditionally, image classification problems treat each class as independent IDs, and people have to train the classification layers with at least a few shots of labeled data per class. The class names are actually also natural language phrases, so we can naturally extend the image-text retrieval capability of ALIGN for image classification without any training data.

The pre-trained image and text encoder can directly be used in classifying an image into a set of classes by retrieving the nearest class name in the aligned embedding space. This approach does not require any training data for the defined class space.

On the ImageNet validation dataset, ALIGN achieves 76.4% top-1 zero-shot accuracy and shows great robustness in different variants of ImageNet with distribution shifts, similar to the concurrent work CLIP. We also use the same text prompt engineering and ensembling as in CLIP.

   ImageNet       ImageNet-R       ImageNet-A       ImageNet-V2   
CLIP 76.2 88.9 77.2 70.1
ALIGN    76.4 92.2 75.8 70.1
Top-1 accuracy of zero-shot classification on ImageNet and its variants.

Application in Image Search
To illustrate the quantitative results above, we build a simple image retrieval system with the embeddings trained by ALIGN and show the top 1 text-to-image retrieval results for a handful of text queries from a 160M image pool. ALIGN can retrieve precise images given detailed descriptions of a scene, or fine-grained or instance-level concepts like landmarks and artworks. These examples demonstrate that the ALIGN model can align images and texts with similar semantics, and that ALIGN can generalize to novel complex concepts.

Image retrieval with fine-grained text queries using ALIGN's embeddings.

Multimodal (Image+Text) Query for Image Search
A surprising property of word vectors is that word analogies can often be solved with vector arithmetic. A common example, "king – man + woman = queen". Such linear relationships between image and text embeddings also emerge in ALIGN.

Specifically, given a query image and a text string, we add their ALIGN embeddings together and use it to retrieve relevant images using cosine similarity, as shown below. These examples not only demonstrate the compositionality of ALIGN embeddings across vision and language domains, but also show the feasibility of searching with a multi-modal query. For instance, one could now look for the "Australia" or "Madagascar" equivalence of pandas, or turn a pair of black shoes into identically-looking beige shoes. Also, it is possible to remove objects/attributes from a scene by performing subtraction in the embedding space, shown below.

Image retrieval with image text queries. By adding or subtracting text query embedding, ALIGN retrieves relevant images.

Social Impact and Future Work
While this work shows promising results from a methodology perspective with a simple data collection method, additional analysis of the data and the resulting model is necessary before the responsible use of the model in practice. For instance, considerations should be made towards the potential for the use of harmful text data in alt-texts to reinforce such harms. With regard to fairness, data balancing efforts may be required to prevent reinforcing stereotypes from the web data. Additional testing and training around sensitive religious or cultural items should be taken to understand and mitigate the impact from possibly mislabeled data.

Further analysis should also be taken to ensure that the demographic distribution of humans and related cultural items, such as clothing, food, and art, do not cause skewed model performance. Analysis and balancing would be required if such models will be used in production.

Conclusion
We have presented a simple method of leveraging large-scale noisy image-text data to scale up visual and vision-language representation learning. The resulting model, ALIGN, is capable of cross-modal retrieval and significantly outperforms SotA models. In visual-only downstream tasks, ALIGN is also comparable to or outperforms SotA models trained with large-scale labeled data.

Acknowledgement
We would like to thank our co-authors in Google Research: Ye Xia, Yi-Ting Chen, Zarana Parekh, Hieu Pham, Quoc V. Le, Yunhsuan Sung, Zhen Li, Tom Duerig. This work was also done with invaluable help from other colleagues from Google. We would like to thank Jan Dlabal and Zhe Li for continuous support in training infrastructure, Simon Kornblith for building the zero-shot & robustness model evaluation on ImageNet variants, Xiaohua Zhai for help on conducting VTAB evaluation, Mingxing Tan and Max Moroz for suggestions on EfficientNet training, Aleksei Timofeev for the early idea of multimodal query retrieval, Aaron Michelony and Kaushal Patel for their early work on data generation, and Sergey Ioffe, Jason Baldridge and Krishna Srinivasan for the insightful feedback and discussion.

Source: Google AI Blog


The Technology Behind Cinematic Photos

Looking at photos from the past can help people relive some of their most treasured moments. Last December we launched Cinematic photos, a new feature in Google Photos that aims to recapture the sense of immersion felt the moment a photo was taken, simulating camera motion and parallax by inferring 3D representations in an image. In this post, we take a look at the technology behind this process, and demonstrate how Cinematic photos can turn a single 2D photo from the past into a more immersive 3D animation.

Camera 3D model courtesy of Rick Reitano.
Depth Estimation
Like many recent computational photography features such as Portrait Mode and Augmented Reality (AR), Cinematic photos requires a depth map to provide information about the 3D structure of a scene. Typical techniques for computing depth on a smartphone rely on multi-view stereo, a geometry method to solve for the depth of objects in a scene by simultaneously capturing multiple photos at different viewpoints, where the distances between the cameras is known. In the Pixel phones, the views come from two cameras or dual-pixel sensors.

To enable Cinematic photos on existing pictures that were not taken in multi-view stereo, we trained a convolutional neural network with encoder-decoder architecture to predict a depth map from just a single RGB image. Using only one view, the model learned to estimate depth using monocular cues, such as the relative sizes of objects, linear perspective, defocus blur, etc.

Because monocular depth estimation datasets are typically designed for domains such as AR, robotics, and self-driving, they tend to emphasize street scenes or indoor room scenes instead of features more common in casual photography, like people, pets, and objects, which have different composition and framing. So, we created our own dataset for training the monocular depth model using photos captured on a custom 5-camera rig as well as another dataset of Portrait photos captured on Pixel 4. Both datasets included ground-truth depth from multi-view stereo that is critical for training a model.

Mixing several datasets in this way exposes the model to a larger variety of scenes and camera hardware, improving its predictions on photos in the wild. However, it also introduces new challenges, because the ground-truth depth from different datasets may differ from each other by an unknown scaling factor and shift. Fortunately, the Cinematic photo effect only needs the relative depths of objects in the scene, not the absolute depths. Thus we can combine datasets by using a scale-and-shift-invariant loss during training and then normalize the output of the model at inference.

The Cinematic photo effect is particularly sensitive to the depth map’s accuracy at person boundaries. An error in the depth map can result in jarring artifacts in the final rendered effect. To mitigate this, we apply median filtering to improve the edges, and also infer segmentation masks of any people in the photo using a DeepLab segmentation model trained on the Open Images dataset. The masks are used to pull forward pixels of the depth map that were incorrectly predicted to be in the background.

Camera Trajectory
There can be many degrees of freedom when animating a camera in a 3D scene, and our virtual camera setup is inspired by professional video camera rigs to create cinematic motion. Part of this is identifying the optimal pivot point for the virtual camera’s rotation in order to yield the best results by drawing one’s eye to the subject.

The first step in 3D scene reconstruction is to create a mesh by extruding the RGB image onto the depth map. By doing so, neighboring points in the mesh can have large depth differences. While this is not noticeable from the “face-on” view, the more the virtual camera is moved, the more likely it is to see polygons spanning large changes in depth. In the rendered output video, this will look like the input texture is stretched. The biggest challenge when animating the virtual camera is to find a trajectory that introduces parallax while minimizing these “stretchy” artifacts.

The parts of the mesh with large depth differences become more visible (red visualization) once the camera is away from the “face-on” view. In these areas, the photo appears to be stretched, which we call “stretchy artifacts”.

Because of the wide spectrum in user photos and their corresponding 3D reconstructions, it is not possible to share one trajectory across all animations. Instead, we define a loss function that captures how much of the stretchiness can be seen in the final animation, which allows us to optimize the camera parameters for each unique photo. Rather than counting the total number of pixels identified as artifacts, the loss function triggers more heavily in areas with a greater number of connected artifact pixels, which reflects a viewer’s tendency to more easily notice artifacts in these connected areas.

We utilize padded segmentation masks from a human pose network to divide the image into three different regions: head, body and background. The loss function is normalized inside each region before computing the final loss as a weighted sum of the normalized losses. Ideally the generated output video is free from artifacts but in practice, this is rare. Weighting the regions differently biases the optimization process to pick trajectories that prefer artifacts in the background regions, rather than those artifacts near the image subject.

During the camera trajectory optimization, the goal is to select a path for the camera with the least amount of noticeable artifacts. In these preview images, artifacts in the output are colored red while the green and blue overlay visualizes the different body regions.

Framing the Scene
Generally, the reprojected 3D scene does not neatly fit into a rectangle with portrait orientation, so it was also necessary to frame the output with the correct right aspect ratio while still retaining the key parts of the input image. To accomplish this, we use a deep neural network that predicts per-pixel saliency of the full image. When framing the virtual camera in 3D, the model identifies and captures as many salient regions as possible while ensuring that the rendered mesh fully occupies every output video frame. This sometimes requires the model to shrink the camera's field of view.

Heatmap of the predicted per-pixel saliency. We want the creation to include as much of the salient regions as possible when framing the virtual camera.

Conclusion
Through Cinematic photos, we implemented a system of algorithms – with each ML model evaluated for fairness – that work together to allow users to relive their memories in a new way, and we are excited about future research and feature improvements. Now that you know how they are created, keep an eye open for automatically created Cinematic photos that may appear in your recent memories within the Google Photos app!

Acknowledgments
Cinematic Photos is the result of a collaboration between Google Research and Google Photos teams. Key contributors also include: Andre Le, Brian Curless, Cassidy Curtis, Ce Liu‎, Chun-po Wang, Daniel Jenstad, David Salesin, Dominik Kaeser, Gina Reynolds, Hao Xu, Huiwen Chang, Huizhong Chen‎, Jamie Aspinall, Janne Kontkanen, Matthew DuVall, Michael Kucera, Michael Milne, Mike Krainin, Mike Liu, Navin Sarma, Orly Liba, Peter Hedman, Rocky Cai‎, Ruirui Jiang‎, Steven Hickson, Tracy Gu, Tyler Zhu, Varun Jampani, Yuan Hao, Zhongli Ding.

Source: Google AI Blog


MediaPipe Holistic — Simultaneous Face, Hand and Pose Prediction, on Device

Real-time, simultaneous perception of human pose, face landmarks and hand tracking on mobile devices can enable a variety of impactful applications, such as fitness and sport analysis, gesture control and sign language recognition, augmented reality effects and more. MediaPipe, an open-source framework designed specifically for complex perception pipelines leveraging accelerated inference (e.g., GPU or CPU), already offers fast and accurate, yet separate, solutions for these tasks. Combining them all in real-time into a semantically consistent end-to-end solution is a uniquely difficult problem requiring simultaneous inference of multiple, dependent neural networks.

Today, we are excited to announce MediaPipe Holistic, a solution to this challenge that provides a novel state-of-the-art human pose topology that unlocks novel use cases. MediaPipe Holistic consists of a new pipeline with optimized pose, face and hand components that each run in real-time, with minimum memory transfer between their inference backends, and added support for interchangeability of the three components, depending on the quality/speed tradeoffs. When including all three components, MediaPipe Holistic provides a unified topology for a groundbreaking 540+ keypoints (33 pose, 21 per-hand and 468 facial landmarks) and achieves near real-time performance on mobile devices. MediaPipe Holistic is being released as part of MediaPipe and is available on-device for mobile (Android, iOS) and desktop. We are also introducing MediaPipe’s new ready-to-use APIs for research (Python) and web (JavaScript) to ease access to the technology.

Top: MediaPipe Holistic results on sport and dance use-cases. Bottom: “Silence” and “Hello” gestures. Note, that our solution consistently identifies a hand as either right (blue color) or left (orange color).

Pipeline and Quality
The MediaPipe Holistic pipeline integrates separate models for pose, face and hand components, each of which are optimized for their particular domain. However, because of their different specializations, the input to one component is not well-suited for the others. The pose estimation model, for example, takes a lower, fixed resolution video frame (256x256) as input. But if one were to crop the hand and face regions from that image to pass to their respective models, the image resolution would be too low for accurate articulation. Therefore, we designed MediaPipe Holistic as a multi-stage pipeline, which treats the different regions using a region appropriate image resolution.

First, MediaPipe Holistic estimates the human pose with BlazePose’s pose detector and subsequent keypoint model. Then, using the inferred pose key points, it derives three regions of interest (ROI) crops for each hand (2x) and the face, and employs a re-crop model to improve the ROI (details below). The pipeline then crops the full-resolution input frame to these ROIs and applies task-specific face and hand models to estimate their corresponding keypoints. Finally, all key points are merged with those of the pose model to yield the full 540+ keypoints.

MediaPipe Holistic pipeline overview.

To streamline the identification of ROIs, a tracking approach similar to the one used for the standalone face and hand pipelines is utilized. This approach assumes that the object doesn't move significantly between frames, using an estimation from the previous frame as a guide to the object region in the current one. However, during fast movements, the tracker can lose the target, which requires the detector to re-localize it in the image. MediaPipe Holistic uses pose prediction (on every frame) as an additional ROI prior to reduce the response time of the pipeline when reacting to fast movements. This also enables the model to retain semantic consistency across the body and its parts by preventing a mixup between left and right hands or body parts of one person in the frame with another.

In addition, the resolution of the input frame to the pose model is low enough that the resulting ROIs for face and hands are still too inaccurate to guide the re-cropping of those regions, which require a precise input crop to remain lightweight. To close this accuracy gap we use lightweight face and hand re-crop models that play the role of spatial transformers and cost only ~10% of the corresponding model's inference time.

 MEH   FLE 
 Tracking pipeline (baseline)   9.8%   3.1% 
 Pipeline without re-crops   11.8%   3.5% 
 Pipeline with re-crops   9.7%   3.1% 
Hand prediction quality.The mean error per hand (MEH) is normalized by the hand size. The face landmarks error (FLE) is normalized by the inter-pupillary distance.

Performance
MediaPipe Holistic requires coordination between up to 8 models per frame — 1 pose detector, 1 pose landmark model, 3 re-crop models and 3 keypoint models for hands and face. While building this solution, we optimized not only machine learning models, but also pre- and post-processing algorithms (e.g., affine transformations), which take significant time on most devices due to pipeline complexity. In this case, moving all the pre-processing computations to GPU resulted in ~1.5 times overall pipeline speedup depending on the device. As a result, MediaPipe Holistic runs in near real-time performance even on mid-tier devices and in the browser.

 Phone   FPS 
 Google Pixel 2 XL   18 
 Samsung S9+   20 
 15-inch MacBook Pro 2017   15 
Performance on various mid-tier devices, measured in frames per second (FPS) using TFLite GPU.

The multi-stage nature of the pipeline provides two more performance benefits. As models are mostly independent, they can be replaced with lighter or heavier versions (or turned off completely) depending on the performance and accuracy requirements. Also, once pose is inferred, one knows precisely whether hands and face are within the frame bounds, allowing the pipeline to skip inference on those body parts.

Applications
MediaPipe Holistic, with its 540+ key points, aims to enable a holistic, simultaneous perception of body language, gesture and facial expressions. Its blended approach enables remote gesture interfaces, as well as full-body AR, sports analytics, and sign language recognition. To demonstrate the quality and performance of the MediaPipe Holistic, we built a simple remote control interface that runs locally in the browser and enables a compelling user interaction, no mouse or keyboard required. The user can manipulate objects on the screen, type on a virtual keyboard while sitting on the sofa, and point to or touch specific face regions (e.g., mute or turn off the camera). Underneath it relies on accurate hand detection with subsequent gesture recognition mapped to a "trackpad" space anchored to the user’s shoulder, enabling remote control from up to 4 meters.

This technique for gesture control can unlock various novel use-cases when other human-computer interaction modalities are not convenient. Try it out in our web demo and prototype your own ideas with it.

In-browser touchless control demos. Left: Palm picker, touch interface, keyboard. Right: Distant touchless keyboard. Try it out!

MediaPipe for Research and Web
To accelerate ML research as well as its adoption in the web developer community, MediaPipe now offers ready-to-use, yet customizable ML solutions in Python and in JavaScript. We are starting with those in our previous publications: Face Mesh, Hands and Pose, including MediaPipe Holistic, with many more to come. Try them directly in the web browser: for Python using the notebooks in MediaPipe on Google Colab, and for JavaScript with your own webcam input in MediaPipe on CodePen!

Conclusion
We hope the release of MediaPipe Holistic will inspire the research and development community members to build new unique applications. We anticipate that these pipelines will open up avenues for future research into challenging domains, such as sign-language recognition, touchless control interfaces, or other complex use cases. We are looking forward to seeing what you can build with it!

Complex and dynamic hand gestures. Videos by Dr. Bill Vicars, used with permission.

Acknowledgments
Special thanks to all our team members who worked on the tech with us: Fan Zhang, Gregory Karpiak, Kanstantsin Sokal, Juhyun Lee, Hadon Nash, Chuo-Ling Chang, Jiuqiang Tang, Nikolay Chirkov, Camillo Lugaresi, George Sung, Michael Hays, Tyler Mullen, Chris McClanahan, Ekaterina Ignasheva, Marat Dukhan, Artsiom Ablavatski, Yury Kartynnik, Karthik Raveendran, Andrei Vakunov, Andrei Tkachenka, Suril Shah, Buck Bourdon, Ming Guang Yong, Esha Uboweja, Siarhei Kazakou, Andrei Kulik, Matsvei Zhdanovich, and Matthias Grundmann.

Source: Google AI Blog


Announcing the Objectron Dataset

The state of the art in machine learning (ML) has achieved exceptional accuracy on many computer vision tasks solely by training models on photos. Building upon these successes and advancing 3D object understanding has great potential to power a wider range of applications, such as augmented reality, robotics, autonomy, and image retrieval. For example, earlier this year we released MediaPipe Objectron, a set of real-time 3D object detection models designed for mobile devices, which were trained on a fully annotated, real-world 3D dataset, that can predict objects’ 3D bounding boxes.

Yet, understanding objects in 3D remains a challenging task due to the lack of large real-world datasets compared to 2D tasks (e.g., ImageNet, COCO, and Open Images). To empower the research community for continued advancement in 3D object understanding, there is a strong need for the release of object-centric video datasets, which capture more of the 3D structure of an object, while matching the data format used for many vision tasks (i.e., video or camera streams), to aid in the training and benchmarking of machine learning models.

Today, we are excited to release the Objectron dataset, a collection of short, object-centric video clips capturing a larger set of common objects from different angles. Each video clip is accompanied by AR session metadata that includes camera poses and sparse point-clouds. The data also contain manually annotated 3D bounding boxes for each object, which describe the object’s position, orientation, and dimensions. The dataset consists of 15K annotated video clips supplemented with over 4M annotated images collected from a geo-diverse sample (covering 10 countries across five continents).

Example videos in the Objectron dataset.

A 3D Object Detection Solution
Along with the dataset, we are also sharing a 3D object detection solution for four categories of objects — shoes, chairs, mugs, and cameras. These models are released in MediaPipe, Google's open source framework for cross-platform customizable ML solutions for live and streaming media, which also powers ML solutions like on-device real-time hand, iris and body pose tracking.

Sample results of 3D object detection solution running on mobile.

In contrast to the previously released single-stage Objectron model, these newest versions utilize a two-stage architecture. The first stage employs the TensorFlow Object Detection model to find the 2D crop of the object. The second stage then uses the image crop to estimate the 3D bounding box while simultaneously computing the 2D crop of the object for the next frame, so that the object detector does not need to run every frame. The second stage 3D bounding box predictor runs at 83 FPS on Adreno 650 mobile GPU.

Diagram of a reference 3D object detection solution.

Evaluation Metric for 3D Object Detection
With ground truth annotations, we evaluate the performance of 3D object detection models using 3D intersection over union (IoU) similarity statistics, a commonly used metric for computer vision tasks, which measures how close the bounding boxes are to the ground truth.

We propose an algorithm for computing accurate 3D IoU values for general 3D-oriented boxes. First, we compute the intersection points between faces of the two boxes using Sutherland-Hodgman Polygon clipping algorithm. This is similar to frustum culling, a technique used in computer graphics. The volume of the intersection is computed by the convex hull of all the clipped polygons. Finally, the IoU is computed from the volume of the intersection and volume of the union of two boxes. We are releasing the evaluation metrics source code along with the dataset.

Compute the 3D intersection over union using the polygon clipping algorithm, Left: Compute the intersection points of each face by clipping the polygon against the box. Right: Compute the volume of intersection by computing the convex hull of all intersection points (green).

Dataset Format
The technical details of the Objectron dataset, including usage and tutorials, are available on the dataset website. The dataset includes bikes, books, bottles, cameras, cereal boxes, chairs, cups, laptops, and shoes, and is stored in the objectron bucket on Google Cloud storage with the following assets:

  • The video sequences
  • The annotation labels (3D bounding boxes for objects)
  • AR metadata (such as camera poses, point clouds, and planar surfaces)
  • Processed dataset: shuffled version of the annotated frames, in tf.example format for images and SequenceExample format for videos.
  • Supporting scripts to run evaluation based on the metric described above
  • Supporting scripts to load the data into Tensorflow, PyTorch, and Jax and to visualize the dataset, including “Hello World” examples

With the dataset, we are also open-sourcing a data-pipeline to parse the dataset in popular Tensorflow, PyTorch and Jax frameworks. Example colab notebooks are also provided.

By releasing this Objectron dataset, we hope to enable the research community to push the limits of 3D object geometry understanding. We also hope to foster new research and applications, such as view synthesis, improved 3D representation, and unsupervised learning. Stay tuned for future activities and developments by joining our mailing list and visiting our github page.

Acknowledgements
The research described in this post was done by Adel Ahmadyan, Liangkai Zhang, Jianing Wei, Artsiom Ablavatski, Mogan Shieh, Ryan Hickman, Buck Bourdon, Alexander Kanaukou, Chuo-Ling Chang, Matthias Grundmann, ‎and Tom Funkhouser. We thank Aliaksandr Shyrokau, Sviatlana Mialik, Anna Eliseeva, and the annotation team for their high quality annotations. We also would like to thank Jonathan Huang and Vivek Rathod for their guidance on TensorFlow Object Detection API.

Source: Google AI Blog


Announcing the Objectron Dataset

The state of the art in machine learning (ML) has achieved exceptional accuracy on many computer vision tasks solely by training models on photos. Building upon these successes and advancing 3D object understanding has great potential to power a wider range of applications, such as augmented reality, robotics, autonomy, and image retrieval. For example, earlier this year we released MediaPipe Objectron, a set of real-time 3D object detection models designed for mobile devices, which were trained on a fully annotated, real-world 3D dataset, that can predict objects’ 3D bounding boxes.

Yet, understanding objects in 3D remains a challenging task due to the lack of large real-world datasets compared to 2D tasks (e.g., ImageNet, COCO, and Open Images). To empower the research community for continued advancement in 3D object understanding, there is a strong need for the release of object-centric video datasets, which capture more of the 3D structure of an object, while matching the data format used for many vision tasks (i.e., video or camera streams), to aid in the training and benchmarking of machine learning models.

Today, we are excited to release the Objectron dataset, a collection of short, object-centric video clips capturing a larger set of common objects from different angles. Each video clip is accompanied by AR session metadata that includes camera poses and sparse point-clouds. The data also contain manually annotated 3D bounding boxes for each object, which describe the object’s position, orientation, and dimensions. The dataset consists of 15K annotated video clips supplemented with over 4M annotated images collected from a geo-diverse sample (covering 10 countries across five continents).

Example videos in the Objectron dataset.

A 3D Object Detection Solution
Along with the dataset, we are also sharing a 3D object detection solution for four categories of objects — shoes, chairs, mugs, and cameras. These models are released in MediaPipe, Google's open source framework for cross-platform customizable ML solutions for live and streaming media, which also powers ML solutions like on-device real-time hand, iris and body pose tracking.

Sample results of 3D object detection solution running on mobile.

In contrast to the previously released single-stage Objectron model, these newest versions utilize a two-stage architecture. The first stage employs the TensorFlow Object Detection model to find the 2D crop of the object. The second stage then uses the image crop to estimate the 3D bounding box while simultaneously computing the 2D crop of the object for the next frame, so that the object detector does not need to run every frame. The second stage 3D bounding box predictor runs at 83 FPS on Adreno 650 mobile GPU.

Diagram of a reference 3D object detection solution.

Evaluation Metric for 3D Object Detection
With ground truth annotations, we evaluate the performance of 3D object detection models using 3D intersection over union (IoU) similarity statistics, a commonly used metric for computer vision tasks, which measures how close the bounding boxes are to the ground truth.

We propose an algorithm for computing accurate 3D IoU values for general 3D-oriented boxes. First, we compute the intersection points between faces of the two boxes using Sutherland-Hodgman Polygon clipping algorithm. This is similar to frustum culling, a technique used in computer graphics. The volume of the intersection is computed by the convex hull of all the clipped polygons. Finally, the IoU is computed from the volume of the intersection and volume of the union of two boxes. We are releasing the evaluation metrics source code along with the dataset.

Compute the 3D intersection over union using the polygon clipping algorithm, Left: Compute the intersection points of each face by clipping the polygon against the box. Right: Compute the volume of intersection by computing the convex hull of all intersection points (green).

Dataset Format
The technical details of the Objectron dataset, including usage and tutorials, are available on the dataset website. The dataset includes bikes, books, bottles, cameras, cereal boxes, chairs, cups, laptops, and shoes, and is stored in the objectron bucket on Google Cloud storage with the following assets:

  • The video sequences
  • The annotation labels (3D bounding boxes for objects)
  • AR metadata (such as camera poses, point clouds, and planar surfaces)
  • Processed dataset: shuffled version of the annotated frames, in tf.example format for images and SequenceExample format for videos.
  • Supporting scripts to run evaluation based on the metric described above
  • Supporting scripts to load the data into Tensorflow, PyTorch, and Jax and to visualize the dataset, including “Hello World” examples

With the dataset, we are also open-sourcing a data-pipeline to parse the dataset in popular Tensorflow, PyTorch and Jax frameworks. Example colab notebooks are also provided.

By releasing this Objectron dataset, we hope to enable the research community to push the limits of 3D object geometry understanding. We also hope to foster new research and applications, such as view synthesis, improved 3D representation, and unsupervised learning. Stay tuned for future activities and developments by joining our mailing list and visiting our github page.

Acknowledgements
The research described in this post was done by Adel Ahmadyan, Liangkai Zhang, Jianing Wei, Artsiom Ablavatski, Mogan Shieh, Ryan Hickman, Buck Bourdon, Alexander Kanaukou, Chuo-Ling Chang, Matthias Grundmann, ‎and Tom Funkhouser. We thank Aliaksandr Shyrokau, Sviatlana Mialik, Anna Eliseeva, and the annotation team for their high quality annotations. We also would like to thank Jonathan Huang and Vivek Rathod for their guidance on TensorFlow Object Detection API.

Source: Google AI Blog


Background Features in Google Meet, Powered by Web ML

Video conferencing is becoming ever more critical in people's work and personal lives. Improving that experience with privacy enhancements or fun visual touches can help center our focus on the meeting itself. As part of this goal, we recently announced ways to blur and replace your background in Google Meet, which use machine learning (ML) to better highlight participants regardless of their surroundings. Whereas other solutions require installing additional software, Meet’s features are powered by cutting-edge web ML technologies built with MediaPipe that work directly in your browser — no extra steps necessary. One key goal in developing these features was to provide real-time, in-browser performance on almost all modern devices, which we accomplished by combining efficient on-device ML models, WebGL-based rendering, and web-based ML inference via XNNPACK and TFLite.

Background blur and background replacement, powered by MediaPipe on the web.

Overview of Our Web ML Solution
The new features in Meet are developed with MediaPipe, Google's open source framework for cross-platform customizable ML solutions for live and streaming media, which also powers ML solutions like on-device real-time hand, iris and body pose tracking.

A core need for any on-device solution is to achieve high performance. To accomplish this, MediaPipe’s web pipeline leverages WebAssembly, a low-level binary code format designed specifically for web browsers that improves speed for compute-heavy tasks. At runtime, the browser converts WebAssembly instructions into native machine code that executes much faster than traditional JavaScript code. In addition, Chrome 84 recently introduced support for WebAssembly SIMD, which processes multiple data points with each instruction, resulting in a performance boost of more than 2x.

Our solution first processes each video frame by segmenting a user from their background (more about our segmentation model later in the post) utilizing ML inference to compute a low resolution mask. Optionally, we further refine the mask to align it with the image boundaries. The mask is then used to render the video output via WebGL2, with the background blurred or replaced.

WebML Pipeline: All compute-heavy operations are implemented in C++/OpenGL and run within the browser via WebAssembly.

In the current version, model inference is executed on the client’s CPU for low power consumption and widest device coverage. To achieve real-time performance, we designed efficient ML models with inference accelerated by the XNNPACK library, the first inference engine specifically designed for the novel WebAssembly SIMD specification. Accelerated by XNNPACK and SIMD, the segmentation model can run in real-time on the web.

Enabled by MediaPipe's flexible configuration, the background blur/replace solution adapts its processing based on device capability. On high-end devices it runs the full pipeline to deliver the highest visual quality, whereas on low-end devices it continues to perform at speed by switching to compute-light ML models and bypassing the mask refinement.

Segmentation Model
On-device ML models need to be ultra lightweight for fast inference, low power consumption, and small download size. For models running in the browser, the input resolution greatly affects the number of floating-point operations (FLOPs) necessary to process each frame, and therefore needs to be small as well. We downsample the image to a smaller size before feeding it to the model. Recovering a segmentation mask as fine as possible from a low-resolution image adds to the challenges of model design.

The overall segmentation network has a symmetric structure with respect to encoding and decoding, while the decoder blocks (light green) also share a symmetric layer structure with the encoder blocks (light blue). Specifically, channel-wise attention with global average pooling is applied in both encoder and decoder blocks, which is friendly to efficient CPU inference.

Model architecture with MobileNetV3 encoder (light blue), and a symmetric decoder (light green).

We modified MobileNetV3-small as the encoder, which has been tuned by network architecture search for the best performance with low resource requirements. To reduce the model size by 50%, we exported our model to TFLite using float16 quantization, resulting in a slight loss in weight precision but with no noticeable effect on quality. The resulting model has 193K parameters and is only 400KB in size.

Rendering Effects
Once segmentation is complete, we use OpenGL shaders for video processing and effect rendering, where the challenge is to render efficiently without introducing artifacts. In the refinement stage, we apply a joint bilateral filter to smooth the low resolution mask.

Rendering effects with artifacts reduced. Left: Joint bilateral filter smooths the segmentation mask. Middle: Separable filters remove halo artifacts in background blur. Right: Light wrapping in background replace.

The blur shader simulates a bokeh effect by adjusting the blur strength at each pixel proportionally to the segmentation mask values, similar to the circle-of-confusion (CoC) in optics. Pixels are weighted by their CoC radii, so that foreground pixels will not bleed into the background. We implemented separable filters for the weighted blur, instead of the popular Gaussian pyramid, as it removes halo artifacts surrounding the person. The blur is performed at a low resolution for efficiency, and blended with the input frame at the original resolution.

Background blur examples.

For background replacement, we adopt a compositing technique, known as light wrapping, for blending segmented persons and customized background images. Light wrapping helps soften segmentation edges by allowing background light to spill over onto foreground elements, making the compositing more immersive. It also helps minimize halo artifacts when there is a large contrast between the foreground and the replaced background.

Background replacement examples.

Performance
To optimize the experience for different devices, we provide model variants at multiple input sizes (i.e., 256x144 and 160x96 in the current release), automatically selecting the best according to available hardware resources.

We evaluated the speed of model inference and the end-to-end pipeline on two common devices: MacBook Pro 2018 with 2.2 GHz 6-Core Intel Core i7, and Acer Chromebook 11 with Intel Celeron N3060. For 720p input, the MacBook Pro can run the higher-quality model at 120 FPS and the end-to-end pipeline at 70 FPS, while the Chromebook runs inference at 62 FPS with the lower-quality model and 33 FPS end-to-end.

 Model   FLOPs   Device   Model Inference   Pipeline 
 256x144   64M   MacBook Pro 18   8.3ms (120 FPS)   14.3ms (70 FPS) 
 160x96   27M   Acer Chromebook 11   16.1ms (62 FPS)   30ms (33 FPS) 
Model inference speed and end-to-end pipeline on high-end (MacBook Pro) and low-end (Chromebook) laptops.

For quantitative evaluation of model accuracy, we adopt the popular metrics of intersection-over-union (IOU) and boundary F-measure. Both models achieve high quality, especially for having such a lightweight network:

  Model     IOU     Boundary  
  F-measure  
  256x144     93.58%     0.9024  
  160x96     90.79%     0.8542  
Evaluation of model accuracy, measured by IOU and boundary F-score.

We also release the accompanying Model Card for our segmentation models, which details our fairness evaluations. Our evaluation data contains images from 17 geographical subregions of the globe, with annotations for skin tone and gender. Our analysis shows that the model is consistent in its performance across the various regions, skin-tones, and genders, with only small deviations in IOU metrics.

Conclusion
We introduced a new in-browser ML solution for blurring and replacing your background in Google Meet. With this, ML models and OpenGL shaders can run efficiently on the web. The developed features achieve real-time performance with low power consumption, even on low-power devices.

Acknowledgments
Special thanks to those on the Meet team and others who worked on this project, in particular Sebastian Jansson, Rikard Lundmark, Stephan Reiter, Fabian Bergmark, Ben Wagner, Stefan Holmer, Dan Gunnarson, Stéphane Hulaud and to all our team members who worked on the technology with us: Siargey Pisarchyk, Karthik Raveendran, Chris McClanahan, Marat Dukhan, Frank Barchard, Ming Guang Yong, Chuo-Ling Chang, Michael Hays, Camillo Lugaresi, Gregory Karpiak, Siarhei Kazakou, Matsvei Zhdanovich, and Matthias Grundmann.

Source: Google AI Blog


Experimenting with Automatic Video Creation From a Web Page

At Google, we're actively exploring how people can use creativity tools powered by machine learning and computational methods when producing multimedia content, from creating music and reframing videos, to drawing and more. One creative process in particular, video production, can especially benefit from such tools, as it requires a series of decisions about what content is best suited to a target audience, how to position the available assets within the field of view, and what temporal arrangement will yield the most compelling narrative. But what if one could leverage existing assets, such as a website, to get a jump-start on video creation? Businesses commonly host websites that contain rich visual representations about their services or products, all of which could be repurposed for other multimedia formats, such as videos, potentially enabling those without extensive resources the ability to reach a broader audience.

In “Automatic Video Creation From a Web Page”, published at UIST 2020, we introduce URL2Video, a research prototype pipeline to automatically convert a web page into a short video, given temporal and visual constraints provided by the content owner. URL2Video extracts assets (text, images, or videos) and their design styles (including fonts, colors, graphical layouts, and hierarchy) from HTML sources and organizes the visual assets into a sequence of shots, while maintaining a look-and-feel similar to the source page. Given a user-specified aspect ratio and duration, it then renders the repurposed materials into a video that is ideal for product and service advertising.

URL2Video Overview
Assume a user provides an URL to a web page that illustrates their business. The URL2Video pipeline automatically selects key content from the page and decides the temporal and visual presentation of each asset, based on a set of heuristics derived from an interview study with designers who were familiar with web design and video ad creation. These designer-informed heuristics capture common video editing styles, including content hierarchy, constraining the amount of information in a shot and its time duration, providing consistent color and style for branding, and more. Using this information, the URL2Video pipeline parses a web page, analyzing the content and selecting visually salient text or images while preserving their design styles, which it organizes according to the video specifications provided by the user.

By extracting the structural content and design from the input web page, URL2Video makes automatic editing decisions to present key messages in a video. It considers the temporal (e.g., the duration in seconds) and spatial (e.g., the aspect ratio) constraints of the output video defined by users.

Webpage Analysis
Given a webpage URL, URL2Video extracts document object model (DOM) information and multimedia materials. For the purposes of our research prototype, we limited the domain to static web pages that contain salient assets and headings preserved in an HTML hierarchy that follows recent web design principles, which encourage the use of prominent elements, distinct sections, and an order of visual focus that guides readers in perceiving information. URL2Video identifies such visually-distinguishable elements as a candidate list of asset groups, each of which may contain a heading, a product image, detailed descriptions, and call-to-action buttons, and captures both the raw assets (text and multimedia files) and detailed design specifications (HTML tags, CSS styles, and rendered locations) for each element. It then ranks the asset groups by assigning each a priority score based on their visual appearance and annotations, including their HTML tags, rendered sizes, and ordering shown on the page. In this way, an asset group that occupies a larger area at the top of the page receives a higher score.

Constraints-Based Asset Selection
We consider two goals when composing a video: (1) each video shot should provide concise information, and (2) the visual design should be consistent with the source page. Based on these goals and the video constraints provided by the user, including the intended video duration (in seconds) and aspect ratio (commonly 16:9, 4:3, 1:1, etc.), URL2Video automatically selects and orders the asset groups to optimize the total priority score. To make the content concise, it presents only dominant elements from a page, such as a headline and a few multimedia assets. It constrains the duration of each visual element for viewers to perceive the content. In this way, a short video highlights the most salient information from the top of the page, and a longer video contains more campaigns or products.

Scene Composition & Video Rendering
Given an ordered list of assets based on the DOM hierarchy, URL2Video follows the design heuristics obtained from interview studies to make decisions about both the temporal and spatial arrangement to present the assets in individual shots. It transfers the graphical layout of elements into the video’s aspect ratio, and applies the style choices including fonts and colors. To make a video more dynamic and engaging, it adjusts the presentation timing of assets. Finally, it renders the content into a video in the MPEG-4 container format.

User Control
The interface to the research prototype allows the user to review the design attributes in each video shot extracted from the source page, reorder the materials, change the detailed design, such as colors and fonts, and adjust the constraints to generate a new video.

In URL2Video's authoring interface (left), users specify the input URL to a source page, size of the target page view, and the output video parameters. URL2Video analyzes the web page and extracts major visual components. It composes a series of scenes and visualizes the key frames as a storyboard. These components are rendered into an output video that satisfies the input temporal and spatial constraints. Users can playback the video, examine the design attributes (bottom-right), and make adjustments to generate video variation, such as reordering the scenes (top-right).

URL2Video Use Cases
We demonstrate the performance of the end-to-end URL2Video pipeline on a variety of existing web pages. Below we highlight an example result where URL2Video converts a page that embeds multiple short video clips into a 12-second output video. Note how the pipeline makes automatic editing decisions on font and color choices, timing, and content ordering in a video captured from the source page.

URL2Video identifies key content from our Google Search introduction page (top), including headings and video assets. It converts them into a video by considering the presentation flow, the source design and the output constraints (a 12-second landscape video; bottom).

The video below provides further demonstration:

To evaluate the automatically-generated videos, we conducted a user study with designers at Google. Our results show that URL2Video effectively extracted design elements from a web page and supported designers by bootstrapping the video creation process.

Next steps
While this current research focuses on the visual presentation, we are developing new techniques that support the audio track and a voiceover in video editing. All in all, we envision a future where creators focus on making high-level decisions and an ML model interactively suggests detailed temporal and graphical edits for a final video creation on multiple platforms.

Acknowledgments
We greatly thank our paper co-authors, Zheng Sun (Research) and Katrina Panovich (YouTube). We would also like to thank our colleagues who contributed to URL2Video, (in alphabetical order of last name) Jordan Canedy, Brian Curless, Nathan Frey, Madison Le, Alireza Mahdian, Justin Parra, Emily Ryan, Mogan Shieh, Sandor Szego, and Weilong Yang. We are grateful to receive the support from our leadership, Tomas Izo, Rahul Sukthankar, and Jay Yagnik.

Source: Google AI Blog


Audiovisual Speech Enhancement in YouTube Stories

While tremendous efforts are invested in improving the quality of videos taken with smartphone cameras, the quality of audio in videos is often overlooked. For example, the speech of a subject in a video where there are multiple people speaking or where there is high background noise might be muddled, distorted, or difficult to understand. In an effort to address this, two years ago we introduced Looking to Listen, a machine learning (ML) technology that uses both visual and audio cues to isolate the speech of a video’s subject. By training the model on a large-scale collection of online videos, we are able to capture correlations between speech and visual signals such as mouth movements and facial expressions, which can then be used to separate the speech of one person in a video from another, or to separate speech from background sounds. We showed that this technology not only achieves state-of-the-art results in speech separation and enhancement (a noticeable 1.5dB improvement over audio-only models), but in particular can improve the results over audio-only processing when there are multiple people speaking, as the visual cues in the video help determine who is saying what.

We are now happy to make the Looking to Listen technology available to users through a new audiovisual Speech Enhancement feature in YouTube Stories (on iOS), allowing creators to take better selfie videos by automatically enhancing their voices and reducing background noise. Getting this technology into users’ hands was no easy feat. Over the past year, we worked closely with users to learn how they would like to use such a feature, in what scenarios, and what balance of speech and background sounds they would like to have in their videos. We heavily optimized the Looking to Listen model to make it run efficiently on mobile devices, overall reducing the running time from 10x real-time on a desktop when our paper came out, to 0.5x real-time performance on the phone. We also put the technology through extensive testing to verify that it performs consistently across different recording conditions and for people with different appearances and voices.

From Research to Product
Optimizing Looking to Listen to allow fast and robust operation on mobile devices required us to overcome a number of challenges. First, all processing needed to be done on-device within the client app in order to minimize processing time and to preserve the user’s privacy; no audio or video information would be sent to servers for processing. Further, the model needed to co-exist alongside other ML algorithms used in the YouTube app in addition to the resource-consuming video recording itself. Finally, the algorithm needed to run quickly and efficiently on-device while minimizing battery consumption.

The first step in the Looking to Listen pipeline is to isolate thumbnail images that contain the faces of the speakers from the video stream. By leveraging MediaPipe BlazeFace with GPU accelerated inference, this step is now able to be executed in just a few milliseconds. We then switched the model part that processes each thumbnail separately to a lighter weight MobileNet (v2) architecture, which outputs visual features learned for the purpose of speech enhancement, extracted from the face thumbnails in 10 ms per frame. Because the compute time to embed the visual features is short, it can be done while the video is still being recorded. This avoids the need to keep the frames in memory for further processing, thereby reducing the overall memory footprint. Then, after the video finishes recording, the audio and the computed visual features are streamed to the audio-visual speech separation model which produces the isolated and enhanced speech.

We reduced the total number of parameters in the audio-visual model by replacing “regular” 2D convolutions with separable ones (1D in the frequency dimension, followed by 1D in the time dimension) with fewer filters. We then optimized the model further using TensorFlow Lite — a set of tools that enable running TensorFlow models on mobile devices with low latency and a small binary size. Finally, we reimplemented the model within the Learn2Compress framework in order to take advantage of built-in quantized training and QRNN support.

Our Looking to Listen on-device pipeline for audiovisual speech enhancement

These optimizations and improvements reduced the running time from 10x real-time on a desktop using the original formulation of Looking to Listen, to 0.5x real-time performance using only an iPhone CPU; and brought the model size down from 120MB to 6MB now, which makes it easier to deploy. Since YouTube Stories videos are short — limited to 15 seconds — the result of the video processing is available within a couple of seconds after the recording is finished.

Finally, to avoid processing videos with clean speech (so as to avoid unnecessary computation), we first run our model only on the first two seconds of the video, then compare the speech-enhanced output to the original input audio. If there is sufficient difference (meaning the model cleaned up the speech), then we enhance the speech throughout the rest of the video.

Researching User Needs
Early versions of Looking to Listen were designed to entirely isolate speech from the background noise. In a user study conducted together with YouTube, we found that users prefer to leave in some of the background sounds to give context and to retain some the general ambiance of the scene. Based on this user study, we take a linear combination of the original audio and our produced clean speech channel: output_audio = 0.1 x original_audio + 0.9 x speech. The following video presents clean speech combined with different levels of the background sounds in the scene (10% background is the balance we use in practice).

Below are additional examples of the enhanced speech results from the new Speech Enhancement feature in YouTube Stories. We recommend watching the videos with good speakers or headphones.

Fairness Analysis
Another important requirement is that the model be fair and inclusive. It must be able to handle different types of voices, languages and accents, as well as different visual appearances. To this end, we conducted a series of tests exploring the performance of the model with respect to various visual and speech/auditory attributes: the speaker’s age, skin tone, spoken language, voice pitch, visibility of the speaker’s face (% of video in which the speaker is in frame), head pose throughout the video, facial hair, presence of glasses, and the level of background noise in the (input) video.

For each of the above visual/auditory attributes, we ran our model on segments from our evaluation set (separate from the training set) and measured the speech enhancement accuracy, broken down according to the different attribute values. Results for some of the attributes are summarized in the following plots. Each data point in the plots represents hundreds (in most cases thousands) of videos fitting the criteria.

Speech enhancement quality (signal-to-distortion ratio, SDR, in dB) for different spoken languages, sorted alphabetically. The average SDR was 7.89 dB with a standard deviation of 0.42 dB — deviation that for human listeners is considered hard to notice.
Left: Speech enhancement quality as a function of the speaker’s voice pitch. The fundamental voice frequency (pitch) of an adult male typically ranges from 85 to 180 Hz, and that of an adult female ranges from 165 to 255 Hz. Right: speech enhancement quality as a function of the speaker’s predicted age.
As our method utilizes facial cues and mouth movements to isolate the speech, we tested whether facial hair (e.g., a moustache, beard) may obstruct those visual cues and affect the method’s performance. Our evaluations show that the quality of speech enhancement is maintained well also in the presence of facial hair.

Using the Feature
YouTube creators who are eligible for YouTube Stories creation may record a video on iOS, and select “Enhance speech” from the volume controls editing tool. This will immediately apply speech enhancement to the audio track and will play back the enhanced speech in a loop. It is then possible to toggle the feature on and off multiple times to compare the enhanced speech with the original audio.

In parallel to this new feature in YouTube, we are also exploring additional venues for this technology. More to come later this year — stay tuned!

Acknowledgements
This feature is a collaboration across multiple teams at Google. Key contributors include: from Research-IL: Oran Lang; from VisCAM: Ariel Ephrat, Mike Krainin, JD Velasquez, Inbar Mosseri, Michael Rubinstein; from Learn2Compress: Arun Kandoor; from MediaPipe: Buck Bourdon, Matsvei Zhdanovich, Matthias Grundmann; from YouTube: Andy Poes, Vadim Lavrusik, Aaron La Lau, Willi Geiger, Simona De Rosa, and Tomer Margolin.

Source: Google AI Blog