The present disclosure provides systems and methods that perform face reconstruction based on an image of a face. In particular, one example system of the present disclosure combines a machine-learned image recognition model with a face modeler that uses a morphable model of a human's facial appearance. The image recognition model can be a deep learning model that generates an embedding in response to receipt of an image (e.g., an uncontrolled image of a face). The example system can further include a small, lightweight, translation model structurally positioned between the image recognition model and the face modeler. The translation model can be a machine-learned model that is trained to receive the embedding generated by the image recognition model and, in response, output a plurality of facial modeling parameter values usable by the face modeler to generate a model of the face.

In various example embodiments, techniques are provided for representing uncertainty when displaying a rendered view of a multi-dimensional mesh (e.g., created by SfM photogrammetry) in a user interface by applying a real-time, obfuscation filter that modifies the rendered view based on uncertainty in screen space. Where the multi-dimensional mesh is within a limit of data accuracy, the rendered view is shown without modification (i.e. as normal), and a user may trust the information displayed. Where the multi-dimensional mesh is beyond the limit of data accuracy, the obfuscation filter obfuscates detail (e.g., by blurring, pixilating, edge enforcing, etc.) in the rendered view so that a user may visually perceive the uncertainty. The amount of obfuscation may be weighted based on uncertainty to allow the user to visually quantify uncertainty.

Disclosed herein are systems for rendering an immersive environment, the systems comprising at least one electronic device configured to be coupled to a body part of a user, the at least one electronic device comprising a sensor, an actuator, or both; a processor capable of being communicatively coupled to the at least one electronic device; and a rendering device capable of being communicatively coupled to the processor. The processor is configured to execute machine-executable instructions that, when executed by the processor, cause the processor to obtain data from or provide data to the at least one electronic device. The rendering device is configured to receive rendering information from the processor, and render the immersive environment based at least in part on the rendering information from the processor.

Disclosed herein are systems for rendering an immersive environment, the systems comprising at least one electronic device configured to be coupled to a body part of a user, the at least one electronic device comprising a sensor, an actuator, or both; a processor capable of being communicatively coupled to the at least one electronic device; and a rendering device capable of being communicatively coupled to the processor. The processor is configured to execute machine-executable instructions that, when executed by the processor, cause the processor to obtain data from or provide data to the at least one electronic device. The rendering device is configured to receive rendering information from the processor, and render the immersive environment based at least in part on the rendering information from the processor.

In various embodiments, a training application generates training items for three-dimensional (3D) pose estimation. The training application generates multiple posed 3D models based on multiple 3D poses and a 3D model of a person wearing a costume that is associated with multiple visual attributes. For each posed 3D model, the training application performs rendering operation(s) to generate synthetic image(s). For each synthetic image, the training application generates a training item based on the synthetic image and the 3D pose associated with the posed 3D model from which the synthetic image was rendered. The synthetic images are included in a synthetic training dataset that is tailored for training a machine-learning model to compute estimated 3D poses of persons from two-dimensional (2D) input images. Advantageously, the synthetic training dataset can be used to train the machine-learning model to accurately infer the orientations of persons across a wide range of environments.

In various embodiments, a training application generates training items for three-dimensional (3D) pose estimation. The training application generates multiple posed 3D models based on multiple 3D poses and a 3D model of a person wearing a costume that is associated with multiple visual attributes. For each posed 3D model, the training application performs rendering operation(s) to generate synthetic image(s). For each synthetic image, the training application generates a training item based on the synthetic image and the 3D pose associated with the posed 3D model from which the synthetic image was rendered. The synthetic images are included in a synthetic training dataset that is tailored for training a machine-learning model to compute estimated 3D poses of persons from two-dimensional (2D) input images. Advantageously, the synthetic training dataset can be used to train the machine-learning model to accurately infer the orientations of persons across a wide range of environments.

Disclosed are systems, methods, and non-transitory computer-readable media for adjusting depth of AR content on HUD. A viewing device identifies, based on sensor data, a physical object visible through a transparent display of the vehicle. The sensor data indicates an initial distance of the physical object from the vehicle. The viewing device gathers virtual content corresponding to the physical object and generates an initial presentation of the virtual content based on the initial distance. The viewing device presents the initial presentation of the virtual content on the transparent display at a position on the transparent display corresponding to the physical object. The viewing device determines, based on updated sensor data, an updated distance of the physical object and generates an updated presentation of the virtual content based on the updated distance. The viewing device presents the updated presentation of the virtual content on the transparent display of the vehicle.

Disclosed are systems, methods, and non-transitory computer-readable media for adjusting depth of AR content on HUD. A viewing device identifies, based on sensor data, a physical object visible through a transparent display of the vehicle. The sensor data indicates an initial distance of the physical object from the vehicle. The viewing device gathers virtual content corresponding to the physical object and generates an initial presentation of the virtual content based on the initial distance. The viewing device presents the initial presentation of the virtual content on the transparent display at a position on the transparent display corresponding to the physical object. The viewing device determines, based on updated sensor data, an updated distance of the physical object and generates an updated presentation of the virtual content based on the updated distance. The viewing device presents the updated presentation of the virtual content on the transparent display of the vehicle.

A method for transforming static two-dimensional images into immersive computer generated content includes various operations performed by a processing system including at least one processor. In one example, the operations include extracting a plurality of physical features of a media asset from a plurality of two-dimensional images of the media asset, constructing a three-dimensional model of the media asset, based on the plurality of physical features, extracting a plurality of narrative elements associated with the media asset from the plurality of two-dimensional images of the media asset, building a hierarchy of a narrative for the media asset, based on at least a subset of the plurality of narrative elements, and creating an immersive experience based on the three-dimensional model and the hierarchy of the narrative.

A method for transforming static two-dimensional images into immersive computer generated content includes various operations performed by a processing system including at least one processor. In one example, the operations include extracting a plurality of physical features of a media asset from a plurality of two-dimensional images of the media asset, constructing a three-dimensional model of the media asset, based on the plurality of physical features, extracting a plurality of narrative elements associated with the media asset from the plurality of two-dimensional images of the media asset, building a hierarchy of a narrative for the media asset, based on at least a subset of the plurality of narrative elements, and creating an immersive experience based on the three-dimensional model and the hierarchy of the narrative.