Abstract: Approaches presented herein provide systems and methods for disentangling identity from expression input models. One or more machine learning systems may be trained directly from three-dimensional (3D) points to develop unique latent codes for expressions associated with different identities. These codes may then be mapped to different identities to independently model an object, such as a face, to generate a new mesh including an expression for an independent identity. A pipeline may include a set of machine learning systems to determine model parameters and also adjust input expression codes using gradient backpropagation in order train models for incorporation into a content development pipeline.

Abstract: One embodiment of the present invention sets forth a technique for performing estimation of scene parameters associated with a two-dimensional (2D) input scene. technique includes identifying, based on the input scene, one or more line segments included in the input scene and generating one or more vanishing points associated with the input scene based on the one or more line segments. The technique also includes estimating, based on the one or more vanishing points, one or more scene parameters associated with the scene and inserting a world object into the input scene based on the one or more scene parameters.

Abstract: One embodiment of the present invention sets forth a technique for estimating a real-world size of an object included in an input scene. The technique includes identifying one or more depictions of human faces included in a two-dimensional input scene and generating one or more bounding boxes associated with the input scene, where each bounding box represents a head size associated with a different one of the one or more depictions of human faces. The technique also includes calculating a relative depth value for each of one or more pixels included in the input scene. The technique further includes calculating an average relative head size based on the one or more bounding boxes and relative depth values associated with the one or more pixels and generating a depth scale based on the average relative head size and a known real-world dimension of an average human head.

Abstract: Generation of three-dimensional (3D) object models may be challenging for users without a sufficient skill set for content creation and may also be resource intensive. One or more style transfer networks may be used for part-aware style transformation of both geometric features and textural components of a source asset to a target asset. The source asset may be segmented into particular parts and then ellipsoid approximations may be warped according to correspondence of the particular parts to the target assets. Moreover, a texture associated with the target asset may be used to warp or adjust a source texture, where the new texture can be applied to the warped parts.

Abstract: Generation of three-dimensional (3D) object models may be challenging for users without a sufficient skill set for content creation and may also be resource intensive. One or more style transfer networks may be combined with a generative network to generate objects based on parameters associated with a textual input. An input including a 3D mesh and texture may be provided to a trained system along with a textual input that includes parameters for object generation. Features of the input object may be identified and then tuned in accordance with the textual input to generate a modified 3D object that includes a new texture along with one or more geometric adjustments.

Abstract: In various examples, information may be received for a 3D model, such as 3D geometry information, lighting information, and material information. A machine learning model may be trained to disentangle the 3D geometry information, the lighting information, and/or material information from input data to provide the information, which may be used to project geometry of the 3D model onto an image plane to generate a mapping between pixels and portions of the 3D model. Rasterization may then use the mapping to determine which pixels are covered and in what manner, by the geometry. The mapping may also be used to compute radiance for points corresponding to the one or more 3D models using light transport simulation. Disclosed approaches may be used in various applications, such as image editing, 3D model editing, synthetic data generation, and/or data set augmentation.

Abstract: In various examples, systems and methods are disclosed relating to generating physics-plausible whole body motion, including determining a mesh sequence corresponding to a motion of at least one dynamic character of one or more dynamic characters and a mesh of a terrain using a video sequence, determining using a generative model and based at least one the mesh sequence and the mesh of the terrain, an occlusion-free motion of the at least one dynamic character by infilling physics-plausible character motions in the mesh sequence for at least one frame of the video sequence that includes an occlusion of at least a portion of the at least one dynamic character, and determining physics-plausible whole body motion of the at least one dynamic character by applying physics-based imitation upon the occlusion-free motion.

Abstract: A method for generating, by an encoder-based model, a three-dimensional (3D) representation of a two-dimensional (2D) image is provided. The encoder-based model is trained to infer the 3D representation using a synthetic training data set generated by a pre-trained model. The pre-trained model is a 3D generative model that produces a 3D representation and a corresponding 2D rendering, which can be used to train a separate encoder-based model for downstream tasks like estimating a triplane representation, neural radiance field, mesh, depth map, 3D key points, or the like, given a single input image, using the pseudo ground truth 3D synthetic training data set. In a particular embodiment, the encoder-based model is trained to predict a triplane representation of the input image, which can then be rendered by a volume renderer according to pose information to generate an output image of the 3D scene from the corresponding viewpoint.

Abstract: In various examples, information may be received for a 3D model, such as 3D geometry information, lighting information, and material information. A machine learning model may be trained to disentangle the 3D geometry information, the lighting information, and/or material information from input data to provide the information, which may be used to project geometry of the 3D model onto an image plane to generate a mapping between pixels and portions of the 3D model. Rasterization may then use the mapping to determine which pixels are covered and in what manner, by the geometry. The mapping may also be used to compute radiance for points corresponding to the one or more 3D models using light transport simulation. Disclosed approaches may be used in various applications, such as image editing, 3D model editing, synthetic data generation, and/or data set augmentation.

Abstract: Apparatuses, systems, and techniques are presented to generate image data. In at least one embodiment, one or more neural networks are used to cause a lighting effect to be applied to one or more objects within one or more images based, at least in part, on synthetically generated images of the one or more objects.

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: A single two-dimensional (2D) image can be used as input to obtain a three-dimensional (3D) representation of the 2D image. This is done by extracting features from the 2D image by an encoder and determining a 3D representation of the 2D image utilizing a trained 2D convolutional neural network (CNN). Volumetric rendering is then run on the 3D representation to combine features within one or more viewing directions, and the combined features are provided as input to a multilayer perceptron (MLP) that predicts and outputs color (or multi-dimensional neural features) and density values for each point within the 3D representation. As a result, single-image inverse rendering may be performed using only a single 2D image as input to create a corresponding 3D representation of the scene in the single 2D image.

Abstract: Generation of three-dimensional (3D) object models may be challenging for users without a sufficient skill set for content creation and may also be resource intensive. One or more style transfer networks may be used for part-aware style transformation of both geometric features and textural components of a source asset to a target asset. The source asset may be segmented into particular parts and then ellipsoid approximations may be warped according to correspondence of the particular parts to the target assets. Moreover, a texture associated with the target asset may be used to warp or adjust a source texture, where the new texture can be applied to the warped parts.

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: Apparatuses, systems, and techniques are presented to generate media content.

Abstract: In various examples, information may be received for a 3D model, such as 3D geometry information, lighting information, and material information. A machine learning model may be trained to disentangle the 3D geometry information, the lighting information, and/or material information from input data to provide the information, which may be used to project geometry of the 3D model onto an image plane to generate a mapping between pixels and portions of the 3D model. Rasterization may then use the mapping to determine which pixels are covered and in what manner, by the geometry. The mapping may also be used to compute radiance for points corresponding to the one or more 3D models using light transport simulation. Disclosed approaches may be used in various applications, such as image editing, 3D model editing, synthetic data generation, and/or data set augmentation.

Abstract: According to an aspect, a method for pose estimation using a convolutional neural network includes extracting features from an image, downsampling the features to a lower resolution, arranging the features into sets of features, where each set of features corresponds to a separate keypoint of a pose of a subject, updating, by at least one convolutional block, each set of features based on features of one or more neighboring keypoints using a kinematic structure, and predicting the pose of the subject using the updated sets of features.

Abstract: According to an aspect, a method for neural rerendering includes obtaining a three-dimensional (3D) model representing a scene of a physical space, where the 3D model is constructed from a collection of input images, rendering an image data buffer from the 3D model according to a viewpoint, where the image data buffer represents a reconstructed image from the 3D model, receiving, by a neural rerendering network, the image data buffer, receiving, by the neural rerendering network, an appearance code representing an appearance condition, and transforming, by the neural rerendering network, the image data buffer into a rerendered image with the viewpoint of the image data buffer and the appearance condition specified by the appearance code.

Abstract: According to an aspect, a method for pose estimation using a convolutional neural network includes extracting features from an image, downsampling the features to a lower resolution, arranging the features into sets of features, where each set of features corresponds to a separate keypoint of a pose of a subject, updating, by at least one convolutional block, each set of features based on features of one or more neighboring keypoints using a kinematic structure, and predicting the pose of the subject using the updated sets of features.