Abstract: A method can include receiving, via a camera, a first video stream of a face of a user; determining a location of the face of the user based on the first video stream and a facial landmark detection model; receiving, via the camera, a second video stream of the face of the user; generating a depth map based on the second video stream, the location of the face of the user, and a depth prediction model; and generating a representation of the user based on the depth map and the second video stream.

Abstract: A method including generating a first vector based on a first grid and a three-dimensional (3D) position associated with a first implicit representation (IR) of a 3D object, generating at least one second vector based on at least one second grid and an upsampled first grid, decoding the first vector to generate a second IR of the 3D object, decoding the at least one second vector to generate at least one third IR of the 3D object, generating a composite IR of the 3D object based on the second IR of the 3D object and the at least one third IR of the 3D object, and generating a reconstructed volume representing the 3D object based on the composite IR of the 3D object.

Abstract: A method comprises receiving a first sequence of images of a portion of a user, the first sequence of images being monocular images; generating an avatar based on the first sequence of images, the avatar being based on a model including a feature vector associated with a vertex; receiving a second sequence of images of the portion of the user; and based on the second sequence of images, modifying the avatar with a displacement of the vertex to represent a gesture of the avatar.

Abstract: A method including predicting a stereo depth associated with a first panoramic image and a second panoramic image, the first panoramic image and the second panoramic image being captured with a time interlude between the capture of the first panoramic image and the second panoramic image, generating a first mesh representation based on the first panoramic image and a stereo depth corresponding to the first panoramic image, generating a second mesh representation based on the second panoramic image and a stereo depth corresponding to the second panoramic image, and synthesizing a third panoramic image based on fusing the first mesh representation with the second mesh representation.

Abstract: Systems and methods for training models to predict dense correspondences across images such as human images. A model may be trained using synthetic training data created from one or more 3D computer models of a subject. In addition, one or more geodesic distances derived from the surfaces of one or more of the 3D models may be used to generate one or more loss values, which may in turn be used in modifying the model's parameters during training.

Abstract: A method can include selecting, from at least a first avatar and a second avatar based on at least one attribute of a calendar event associated with a user, a session avatar, the first avatar being based on a first set of images of a user wearing a first outfit and the second avatar being based on a second set of images of the user wearing a second outfit, and presenting the session avatar during a videoconference, the presentation of the session avatar changing based on audio input received from the user during the videoconference.

Abstract: Systems and methods for training models to predict dense correspondences across images such as human images. A model may be trained using synthetic training data created from one or more 3D computer models of a subject. In addition, one or more geodesic distances derived from the surfaces of one or more of the 3D models may be used to generate one or more loss values, which may in turn be used in modifying the model's parameters during training.

Abstract: A system including a computer vision model configured to perform a machine learning task is described. The computer vision model includes multiple wrapped convolutional layers, in which each wrapped convolutional layer includes a respective convolutional layer configured to receive, for each time step of multiple time steps, a layer input and to process the layer input to generate an initial output for the current time step, and a respective note-taking module configured to receive the initial output and to process the initial output to generate a feature vector for the current time step, the feature vector representing local information of the wrapped convolutional layer. The model includes a summarization module configured to receive the feature vectors and to process the feature vectors to generate a revision vector for the current time step, the revision vector representing global information of the plurality of wrapped convolutional layers.

Abstract: Systems and methods for training models to predict dense correspondences across images such as human images. A model may be trained using synthetic training data created from one or more 3D computer models of a subject. In addition, one or more geodesic distances derived from the surfaces of one or more of the 3D models may be used to generate one or more loss values, which may in turn be used in modifying the model's parameters during training.

Abstract: Techniques include introducing a neural generator configured to produce novel faces that can be rendered at free camera viewpoints (e.g., at any angle with respect to the camera) and relit under an arbitrary high dynamic range (HDR) light map. A neural implicit intrinsic field takes a randomly sampled latent vector as input and produces as output per-point albedo, volume density, and reflectance properties for any queried 3D location. These outputs are aggregated via a volumetric rendering to produce low resolution albedo, diffuse shading, specular shading, and neural feature maps. The low resolution maps are then upsampled to produce high resolution maps and input into a neural renderer to produce relit images.

Abstract: Example embodiments relate to techniques for volumetric performance capture with neural rendering. A technique may involve initially obtaining images that depict a subject from multiple viewpoints and under various lighting conditions using a light stage and depth data corresponding to the subject using infrared cameras. A neural network may extract features of the subject from the images based on the depth data and map the features into a texture space (e.g., the UV texture space). A neural renderer can be used to generate an output image depicting the subject from a target view such that illumination of the subject in the output image aligns with the target view. The neural render may resample the features of the subject from the texture space to an image space to generate the output image.

Abstract: According to an aspect, a real-time active stereo system includes a capture system configured to capture stereo data, where the stereo data includes a first input image and a second input image, and a depth sensing computing system configured to predict a depth map. The depth sensing computing system includes a feature extractor configured to extract features from the first and second images at a plurality of resolutions, an initialization engine configured to generate a plurality of depth estimations, where each of the plurality of depth estimations corresponds to a different resolution, and a propagation engine configured to iteratively refine the plurality of depth estimations based on image warping and spatial propagation.

Abstract: An electronic device estimates a depth map of an environment based on matching reduced-resolution stereo depth images captured by depth cameras to generate a coarse disparity (depth) map. The electronic device downsamples depth images captured by the depth cameras and matches sections of the reduced-resolution images to each other to generate a coarse depth map. The electronic device upsamples the coarse depth map to a higher resolution and refines the upsampled depth map to generate a high-resolution depth map to support location-based functionality.

Abstract: Systems and methods are directed to encoding and/or decoding of the textures/geometry of a three-dimensional volumetric representation. An encoding computing system can obtain voxel blocks from a three-dimensional volumetric representation of an object. The encoding computing system can encode voxel blocks with a machine-learned voxel encoding model to obtain encoded voxel blocks. The encoding computing system can decode the encoded voxel blocks with a machine-learned voxel decoding model to obtain reconstructed voxel blocks. The encoding computing system can generate a reconstructed mesh representation of the object based at least in part on the one or more reconstructed voxel blocks. The encoding computing system can encode textures associated with the voxel blocks according to an encoding scheme and based at least in part on the reconstructed mesh representation of the object to obtain encoded textures.

Abstract: An electronic device estimates a depth map of an environment based on matching reduced-resolution stereo depth images captured by depth cameras to generate a coarse disparity (depth) map. The electronic device downsamples depth images captured by the depth cameras and matches sections of the reduced-resolution images to each other to generate a coarse depth map. The electronic device upsamples the coarse depth map to a higher resolution and refines the upsampled depth map to generate a high-resolution depth map to support location-based functionality.

Abstract: A computer-implemented method includes receiving a two-dimensional (2-D) side view face image of a person, identifying a bounded portion or area of the 2-D side view face image of the person as an ear region-of-interest (ROI) area showing at least a portion of an ear of the person, and processing the identified ear ROI area of the 2-D side view face image, pixel-by-pixel, through a trained fully convolutional neural network model (FCNN model) to predict a 2-D ear saddle point (ESP) location for the ear shown in the ear ROI area. The FCNN model has an image segmentation architecture.

Abstract: Example implementations relate to joint depth prediction from dual cameras and dual pixels. An example method may involve obtaining a first set of depth information representing a scene from a first source and a second set of depth information representing the scene from a second source. The method may further involve determining, using a neural network, a joint depth map that conveys respective depths for elements in the scene. The neural network may determine the joint depth map based on a combination of the first set of depth information and the second set of depth information. In addition, the method may involve modifying an image representing the scene based on the joint depth map. For example, background portions of the image may be partially blurred based on the joint depth map.

Abstract: A network for neural pose transfer includes a pose feature extractor, and a style transfer decoder, wherein the pose feature extractor comprises a plurality of sequential extracting stacks, each extracting stack consists of a first convolution layer and an Instance Norm layer sequential to the first convolution layer. The style transfer decoder comprises a plurality of sequential decoding stacks, a second convolution layer sequential to the plurality of decoding stacks and a tan h layer sequential to the second convolution layer. Each decoding stack consists of a third convolution layer and a SPAdaIn residual block. A source pose mesh is input to the pose feature extractor, and an identity mesh is concatenated with the output of the pose feature extractor and meanwhile fed to each SPAdaIn residual block of the style transfer decoder. A system thereof is also provided.

Abstract: A network for neural pose transfer includes a pose feature extractor, and a style transfer decoder, wherein the pose feature extractor comprises a plurality of sequential extracting stacks, each extracting stack consists of a first convolution layer and an Instance Norm layer sequential to the first convolution layer. The style transfer decoder comprises a plurality of sequential decoding stacks, a second convolution layer sequential to the plurality of decoding stacks and a tan h layer sequential to the second convolution layer. Each decoding stack consists of a third convolution layer and a SPAdaIn residual block. A source pose mesh is input to the pose feature extractor, and an identity mesh is concatenated with the output of the pose feature extractor and meanwhile fed to each SPAdaIn residual block of the style transfer decoder. A system thereof is also provided.

Abstract: According to an aspect, a real-time active stereo system includes a capture system configured to capture stereo data, where the stereo data includes a first input image and a second input image, and a depth sensing computing system configured to predict a depth map. The depth sensing computing system includes a feature extractor configured to extract features from the first and second images at a plurality of resolutions, an initialization engine configured to generate a plurality of depth estimations, where each of the plurality of depth estimations corresponds to a different resolution, and a propagation engine configured to iteratively refine the plurality of depth estimations based on image warping and spatial propagation.