Abstract: Techniques for aligning object representations for animation include analyzing a source object representation and a target object representation to identify a category of the source object and a category of the target object. Based on the category or categories of the objects, a feature extraction machine learning models is selected. The source object representation and the target object representation are provided as input to the selected feature extraction machine learning model to generate respective semantic descriptors and shape vectors for the source and target objects. Based on the semantic descriptors and the shape vectors for the source and target objects, an alignment machine learning model generates an aligned target object representation that is aligned with the source object representation and usable for animating the target object.

Abstract: Techniques are disclosed for interactive editing of virtual three-dimensional scenes. In the disclosed techniques, rendering is divided into (1) an interactive phase during which a user interactively edits a virtual scene while preview image frames are rendered using a modified ray tracing technique, and (2) a refinement phase during which full ray tracing is performed to show the user a final rendered image frame. The modified ray tracing technique may limit the number of bounces of light rays and/or the computations performed at each bounce, thereby reducing computational expense relative to a full ray tracing technique. Further, the modified ray tracing technique may be user-selectable and associated with a particular department within an animation studio.

Abstract: Techniques are disclosed for interactive editing of virtual three-dimensional scenes. In the disclosed techniques, rendering is divided into (1) an interactive phase during which a user interactively edits a virtual scene while preview image frames are rendered using a modified ray tracing technique, and (2) a refinement phase during which full ray tracing is performed to show the user a final rendered image frame. The modified ray tracing technique may limit the number of bounces of light rays and/or the computations performed at each bounce, thereby reducing computational expense relative to a full ray tracing technique. Further, the modified ray tracing technique may be user-selectable and associated with a particular department within an animation studio.

Abstract: Techniques are disclosed for interactive editing of virtual three-dimensional scenes. In the disclosed techniques, rendering is divided into (1) an interactive phase during which a user interactively edits a virtual scene while preview image frames are rendered using a modified ray tracing technique, and (2) a refinement phase during which full ray tracing is performed to show the user a final rendered image frame. The modified ray tracing technique may limit the number of bounces of light rays and/or the computations performed at each bounce, thereby reducing computational expense relative to a full ray tracing technique. Further, the modified ray tracing technique may be user-selectable and associated with a particular department within an animation studio.

Abstract: Techniques are disclosed for interactive editing of virtual three-dimensional scenes. In the disclosed techniques, rendering is divided into (1) an interactive phase during which a user interactively edits a virtual scene while preview image frames are rendered using a modified ray tracing technique, and (2) a refinement phase during which full ray tracing is performed to show the user a final rendered image frame. The modified ray tracing technique may limit the number of bounces of light rays and/or the computations performed at each bounce, thereby reducing computational expense relative to a full ray tracing technique. Further, the modified ray tracing technique may be user-selectable and associated with a particular department within an animation studio.

Abstract: A method for a computer system includes receiving a plurality of values for an illumination parameter associated with an illumination source for a scene, determining a plurality illumination contributions for a surface of an object within the scene, in response to the plurality of values, determining a plurality of texture maps associated with the surface of the object in response to the plurality of illumination contributions, wherein each of the plurality of texture maps is associated with each of the plurality of values for the illumination parameter, receiving a value for the illumination parameter at render time from a user, determining a texture map associated with the surface of the object, in response to the value for the illumination parameter and in response to the plurality of texture maps, rendering the surface of the object using the texture map to form an image, and displaying the image to the user.

Abstract: Textures are transferred between different object models using a point cloud. In a first phase, a point cloud in 3-D space is created to represent a texture map as applied to a first, or “source,” object model. In a second phase, a value for a target texel of a texture map associated with a second, or “target,” object model, is determined by identifying the 3-D location on a surface defined by the target object model that maps to the location of the target texel and assigning a value based on the nearest point (or points) to that location in the 3-D point cloud. To the extent that differences between the source and target object models are minor, the texture transfer can be accomplished without loss of information or manual cleanup.

Abstract: Textures are transferred between different object models using a point cloud. In a first phase, a point cloud in 3-D space is created to represent a texture map as applied to a first, or “source,” object model. In a second phase, a value for a target texel of a texture map associated with a second, or “target,” object model, is determined by identifying the 3-D location on a surface defined by the target object model that maps to the location of the target texel and assigning a value based on the nearest point (or points) to that location in the 3-D point cloud. To the extent that differences between the source and target object models are minor, the texture transfer can be accomplished without loss of information or manual cleanup.

Abstract: A method for a computer system includes receiving a plurality of values for an illumination parameter associated with an illumination source for a scene, determining a plurality illumination contributions for a surface of an object within the scene, in response to the plurality of values, determining a plurality of texture maps associated with the surface of the object in response to the plurality of illumination contributions, wherein each of the plurality of texture maps is associated with each of the plurality of values for the illumination parameter, receiving a value for the illumination parameter at render time from a user, determining a texture map associated with the surface of the object, in response to the value for the illumination parameter and in response to the plurality of texture maps, rendering the surface of the object using the texture map to form an image, and displaying the image to the user.