Abstract: Examples are disclosed that relate to generating expressive avatars using multi-modal three-dimensional face modeling and tracking. One example includes a computer system comprising a processor coupled to a storage system that stores instructions. Upon execution by the processor, the instructions cause the processor to receive initialization data describing an initial state of a facial model. The instructions further cause the processor to receive a plurality of multi-modal data signals. The instructions further cause the processor to perform a fitting process using the initialization data and the plurality of multi-modal data signals. The instructions further cause the processor to determine a set of parameters based on the fitting process, wherein the determined set of parameters describes an updated state of the facial model.

Abstract: Computing an image depicting a face having an expression with wrinkles is described. A 3D polygon mesh model of a face has a non-neutral expression. A tension map is computed from the 3D polygon mesh model. A neutral texture, a compressed wrinkle texture and an expanded wrinkle texture are computed or obtained from a library. The neutral texture comprises a map of the first face with a neutral expression. The compressed wrinkle texture is a map of the first face formed by aggregating maps of the first face with different expressions using the tension map, and the expanded wrinkle texture comprises a map of the first face formed by aggregating maps of the first face with different expressions using the tension map. A graphics engine may be used to apply the wrinkle textures to the 3D model according to the tension map; and render the image from the 3D model.

Abstract: Systems and methods are provided that are directed to generating video sequences including physio-realistic avatars. In examples, an albedo for an avatar is received, a sub-surface skin color associated with the albedo is modified based on physiological data associated with physiologic characteristic, and an avatar based on the albedo and the modified sub-surface skin color is rendered. The rendered avatar may then be synthesized in a frame of video. In some examples, a video including the synthesized avatar may be used to train a machine learning model to detect a physiological characteristic. The machine learning model may receive a plurality of video segments, where one or more of the video segments includes a synthetic physio-realistic avatar generated with the physiological characteristic. The machine learning model may be trained using the plurality of video segments. The trained model may be provided to a requesting entity.

Abstract: In various examples there is a method of image processing comprising: storing a real image of an object in memory, the object being a specified type of object. The method involves computing, using a first encoder, a factorized embedding of the real image. The method receives a value of at least one parameter of a synthetic image rendering apparatus for rendering synthetic images of objects of the specified type. The parameter controls an attribute of synthetic images of objects rendered by the rendering apparatus. The method computes an embedding factor of the received value using a second encoder. The factorized embedding is modified with the computed embedding factor. The method computes, using a decoder with the modified embedding as input, an output image of an object which is substantially the same as the real image except for the attribute controlled by the parameter.

Abstract: Systems and methods are provided that are directed to generating video sequences including physio-realistic avatars. In examples, an albedo for an avatar is received, a sub-surface skin color associated with the albedo is modified based on physiological data associated with physiologic characteristic, and an avatar based on the albedo and the modified sub-surface skin color is rendered. The rendered avatar may then be synthesized in a frame of video. In some examples, a video including the synthesized avatar may be used to train a machine learning model to detect a physiological characteristic. The machine learning model may receive a plurality of video segments, where one or more of the video segments includes a synthetic physio-realistic avatar generated with the physiological characteristic. The machine learning model may be trained using the plurality of video segments. The trained model may be provided to a requesting entity.

Abstract: The techniques described herein disclose a system that is configured to detect and track the three-dimensional pose of an object (e.g., a head-mounted display device) in a color image using an accessible three-dimensional model of the object. The system uses the three-dimensional pose of the object to repair pixel depth values associated with a region (e.g., a surface) of the object that is composed of material that absorbs light emitted by a time-of-flight depth sensor to determine depth. Consequently, a color-depth image (e.g., a Red-Green-Blue-Depth image or RGB-D image) can be produced that does not include dark holes on and around the region of the object that is composed of material that absorbs light emitted by the time-of-flight depth sensor.

Abstract: Keypoints are predicted in an image. Predictions are generated for each of the keypoints of an image as a 2D random variable, normally distributed with location (x, y) and standard deviation sigma. A neural network is trained to maximize a log-likelihood that samples from each of the predicted keypoints equal a ground truth. The trained neural network is used to predict keypoints of an image without generating a heatmap.

Abstract: Keypoints are predicted in an image. A neural network is executed that is configured to predict each of the keypoints as a 2D random variable, normally distributed with a 2D position and 2×2 covariance matrix. The neural network is trained to maximize a log-likelihood that samples from each of the predicted keypoints equal a ground truth. The trained neural network is used to predict keypoints of an image without generating a heatmap.

Abstract: In various examples there is a method of image processing comprising: storing a real image of an object in memory, the object being a specified type of object. The method involves computing, using a first encoder, a factorized embedding of the real image. The method receives a value of at least one parameter of a synthetic image rendering apparatus for rendering synthetic images of objects of the specified type. The parameter controls an attribute of synthetic images of objects rendered by the rendering apparatus. The method computes an embedding factor of the received value using a second encoder. The factorized embedding is modified with the computed embedding factor. The method computes, using a decoder with the modified embedding as input, an output image of an object which is substantially the same as the real image except for the attribute controlled by the parameter.

Abstract: There is a region of interest of a synthetic image depicting an object from a class of objects. A trained neural image generator, having been trained to map embeddings from a latent space to photorealistic images of objects in the class, is accessed. A first embedding is computed from the latent space, the first embedding corresponding to an image which is similar to the region of interest while maintaining photorealistic appearance. A second embedding is computed from the latent space, the second embedding corresponding to an image which matches the synthetic image. Blending of the first embedding and the second embedding is done to form a blended embedding. At least one output image is generated from the blended embedding, the output image being more photorealistic than the synthetic image.

Abstract: There is a region of interest of a synthetic image depicting an object from a class of objects. A trained neural image generator, having been trained to map embeddings from a latent space to photorealistic images of objects in the class, is accessed. A first embedding is computed from the latent space, the first embedding corresponding to an image which is similar to the region of interest while maintaining photorealistic appearance. A second embedding is computed from the latent space, the second embedding corresponding to an image which matches the synthetic image. Blending of the first embedding and the second embedding is done to form a blended embedding. At least one output image is generated from the blended embedding, the output image being more photorealistic than the synthetic image.

Abstract: Systems and methods are provided that are directed to generating video sequences including physio-realistic avatars. In examples, an albedo for an avatar is received, a sub-surface skin color associated with the albedo is modified based on physiological data associated with physiologic characteristic, and an avatar based on the albedo and the modified sub-surface skin color is rendered. The rendered avatar may then be synthesized in a frame of video. In some examples, a video including the synthesized avatar may be used to train a machine learning model to detect a physiological characteristic. The machine learning model may receive a plurality of video segments, where one or more of the video segments includes a synthetic physio-realistic avatar generated with the physiological characteristic. The machine learning model may be trained using the plurality of video segments. The trained model may be provided to a requesting entity.

Abstract: In various examples there is an apparatus for computing an image depicting a face of a wearer of a head mounted display (HMD), as if the wearer was not wearing the HMD. An input image depicts a partial view of the wearer's face captured from at least one face facing capture device in the HMD. A machine learning apparatus is available which has been trained to compute expression parameters from the input image. A 3D face model that has expressions parameters is accessible as well as a photorealiser being a machine learning model trained to map images rendered from the 3D face model to photorealistic images. The apparatus computes expression parameter values from the image using the machine learning apparatus. The apparatus drives the 3D face model with the expression parameter values to produce a 3D model of the face of the wearer and then renders the 3D model from a specified viewpoint to compute a rendered image. The rendered image is upgraded to a photorealistic image using the photorealiser.

Abstract: There is a region of interest of a synthetic image depicting an object from a class of objects. A trained neural image generator, having been trained to map embeddings from a latent space to photorealistic images of objects in the class, is accessed. A first embedding is computed from the latent space, the first embedding corresponding to an image which is similar to the region of interest while maintaining photorealistic appearance. A second embedding is computed from the latent space, the second embedding corresponding to an image which matches the synthetic image. Blending of the first embedding and the second embedding is done to form a blended embedding. At least one output image is generated from the blended embedding, the output image being more photorealistic than the synthetic image.

Abstract: In various examples there is a method of image processing comprising: storing a real image of an object in memory, the object being a specified type of object. The method involves computing, using a first encoder, a factorized embedding of the real image. The method receives a value of at least one parameter of a synthetic image rendering apparatus for rendering synthetic images of objects of the specified type. The parameter controls an attribute of synthetic images of objects rendered by the rendering apparatus. The method computes an embedding factor of the received value using a second encoder. The factorized embedding is modified with the computed embedding factor. The method computes, using a decoder with the modified embedding as input, an output image of an object which is substantially the same as the real image except for the attribute controlled by the parameter.