Facebook, Inc.

Leland Stanford Junior University

Meta Platforms, Inc.

Peter Vajda

Peizhao Zhang

Yanghan Wang

John Samuel Barnett

Congxi Lu

Jonathan Morton

Joshua Charles Harris

Dantley Davis

Brian Keith Cabral

Forrest Samuel Briggs

Albert Parra Pozo

Fei Yang

David Chen

Shen Wang

Bernd Girod

Matthieu Tony Uyttendaele

Huizhong Chen

Ross Girshick

Xiaoliang Dai

Shanghsuan Tsai

Yuandong Tian

Zijian He

Yangqing Jia

Matthew William Canton

Tommer Leyvand

Matthew Chuck-Jun Yu

Bichen Wu

Andre Filgueiras De Araujo

Kevin Matzen

Priyam Chatterjee

Maria Loveva

Shihang Wei

Dmitrii Marin

Han Wang

Justin Johnson

Maryam Daneshi

Computer implemented systems are described that implement a differentiable neural architecture search (DNAS) engine executing on one or more processors. The DNAS engine is configured with a stochastic super net defining a layer-wise search space having a plurality of candidate layers, each of the candidate layers specifying one or more operators for a neural network architecture. Further, the DNAS engine is configured to process training data to train weights for the operators in the stochastic super net based on a loss function representing a latency of the respective operator on a target platform, and to select a set of candidate neural network architectures from the trained stochastic super net. The DNAS engine may, for example, be configured to train the stochastic super net by traversing the layer-wise search space using gradient-based optimization of network architecture distribution.

Hardware-aware efficient neural network design system having differentiable neural architecture search

Systems, methods, and non-transitory computer readable media can determine a placement in a camera view for displaying an augmented reality (AR) advertisement, where the camera view is associated with a computing device. An AR advertisement for a user associated with the computing device can be determined based on attributes associated with the user. Display of the AR advertisement can be caused at the determined placement in the camera view.

Systems and methods for providing augmented reality personalized content

Techniques are described for content-adaptive downsampling of digital images and videos for computer vision operations, such as semantic segmentation. A computer vision system comprises a memory, one or more processors operably coupled to the memory and a downsampling module configured for execution by the one or more processors to perform, based on a non-uniform sampling model trained to predict content-aware sampling parameters, downsampling input image data to generate downsampled image data. A segmentation module is configured for execution by the one or more processors to perform segmentation on the downsampled image to produce a segmentation result, such as a feature map that assigns pixels of the downsampled image data to object classes. An upsampling module is configured for execution by the one or more processors to perform upsampling according to the segmentation result to produce upsampled image data.

Content-adaptive non-uniform image downsampling using predictive auxiliary convolutional neural network

Systems, methods, and non-transitory computer-readable media can identify a first user depicted in image content captured by a second user. It is determined that the first user should be obscured in the image content based on privacy settings. The image content is modified to obscure the first user.

Systems and methods for providing augmented reality overlays

In one embodiment, a system accesses a probability model associated with an image depicting a body. The probability model includes probability values associated with regions of the image and each probability value represents a probability of the associated region of the image containing a particular body part. The system selects a subset (e.g., 3) of the probability values based on a comparison of the probability values. For each selected probability value, the system identifies surrounding probability values surrounding the selected probability value and computes a probabilistic maximum based on the selected probability value and the surrounding probability values. Each probabilistic maximum is associated with a location within the regions associated with the selected probability value and the surrounding probability values. One of the locations associated with the probabilistic maxima is then selected, which represents a determined location in the image that corresponds to the particular body part in the image.

Optimizations for structure mapping and up-sampling

In one embodiment, a system may access first, second, and third probability models that are respectively associated with predetermined first and second body parts and a predetermined segment connecting the first and second body parts. Each model includes probability values associated with regions in an image, with each value representing the probability of the associated region containing the associated body part or segment. The system may select a first and second region based on the first probability model and a third region based on the second probability model. Based on the third probability model, the system may compute a first probability score for regions connecting the first and third regions and a second probability score for regions connecting the second and third regions. Based on the first and second probability scores, the system may select the first region to indicate where the predetermined first body part appears in the image.

Systems and methods for optimizing pose estimation

In one embodiment, a system may access an image and generate a feature map for the image using a neural network. The system may identify regions of interest in the feature map. Regional feature maps may be generated for the regions of interest, respectively. Each of the regional feature maps has a first, a second, and a third dimension. The system may generate a first combined regional feature map by combining the regional feature maps. The combined regional feature map has a first, a second, and a third dimension. The system may generate a second combined regional feature map by processing the first combined regional feature map using one or more convolutional layers. The system may generate, for each of the regions of interest, information associated with an object instance based on a portion of the second combined regional feature map associated with that region of interest.

Optimizations for dynamic object instance detection, segmentation, and structure mapping

One general aspect includes a method, including: capturing an image of an object having a multi-part identifier displayed thereon, the multi-part identifier including a first portion and a second portion, the first portion including graphical content and the second portion including human-recognizable textual content. The method also includes based on the captured image, identifying a domain associated with the graphical content. The method also includes based on the captured image, identifying a sub-part of the domain associated with the textual content. The method also includes identifying a digital destination based on the identified domain and the identified sub-part. The method also includes performing an action based on the digital destination. Other embodiments of this aspect include corresponding computer systems, apparatus, and computer programs recorded on one or more computer storage devices, each configured to perform the actions of the methods.

System and method for determination of a digital destination based on a multi-part identifier

In one embodiment, a system accesses pose probability models for predetermined parts of a body depicted in an image. Each of the pose probability models is configured for determining a probability of the associated predetermined body part being at a location in the image. The system determines a candidate pose that is defined by a set of coordinates representing candidate locations of the predetermined body parts. The system further determines a first probability score for the candidate pose based on the pose probability models and the set of coordinates of the candidate pose. A pose representation is generated for the candidate pose using a transformation model and the candidate pose. The system determines a second probability score for the pose representation based on a pose-representation probability model. The system selects the candidate pose to represent a pose of the body based on at least the first and second probability scores.

In one embodiment, a method includes a system accessing an image and generating a feature map using a first neural network. The system identifies a plurality of regions of interest in the feature map. A plurality of regional feature maps may be generated for the plurality of regions of interest, respectively. Using a second neural network, the system may detect at least one regional feature map in the plurality of regional feature maps that corresponds to a person depicted in the image, and generate a target region definition associated with a location of the person using the regional feature map. Based on the target region definition associated with the location of the person, a target regional feature map may be generated by sampling the feature map for the image. The system may process the target regional feature map to generate a keypoint mask and an instance segmentation mask.

Systems, methods, and non-transitory computer-readable media can identify one or more objects depicted in a camera view of a camera application displayed on a display of a user device. An augmented reality overlay is determined based on the one or more objects identified in the camera view. The camera view is modified based on the augmented reality overlay.

A canvas generation system generates a canvas view of a scene based on a set of original camera views depicting the scene, for example to recreate a scene in virtual reality. Canvas views can be generated based on a set of synthetic views generated from a set of original camera views. Synthetic views can be generated, for example, by shifting and blending relevant original camera views based on an optical flow across multiple original camera views. An optical flow can be generated using an iterative method which individually optimizes the optical flow vector for each pixel of a camera view and propagates changes in the optical flow to neighboring optical flow vectors.

Efficient canvas view generation from intermediate views

Efficient determination of optical flow between images

An image processing system transforms content images into the style of another reference style image. For example, the system applies a noise mask to generate noisy versions of the content images. The system then recomposes a content image in the style of a reference image by applying computer models to the noisy version of the content image, which reduces artifacts in the stylized image compared to that of a stylized image generated by applying the computer models to the original content image. When the content images are part of a video sequence, the image processing system may adjust the noise mask applied in a subsequent frame such that it tracks the movement of the client device from the current frame to the subsequent frame. This allows the system to reduce artifacts while stylizing the frames of the video in a consistent manner.

Growing community of inventors

Palo Alto, CA, United States of America

Peter Vajda