Abstract: Embodiments of the present disclosure relate to real-time neural appearance models. Using a neural decoder, scenes are rendered in real-time with complex material appearance previously reserved for offline use. Learned hierarchical textures representing the material properties are encoded as latent codes. When a ray is cast and intersects with geometry in the scene, the intersection point is mapped to one of the latent codes. The latent code is interpreted using neural decoders, which produce reflectance values and importance-sampled directions that can be used to determine a pixel color.

Abstract: Apparatuses, systems, and techniques to generate pixels based on other pixels. In at least one embodiment, one or more neural networks are used to generate one or more pixels based, at least in part, on sets of pixels surrounding the one or more pixels.

Abstract: A technique is described for extracting or constructing a three-dimensional (3D) model from multiple two-dimensional (2D) images. In an embodiment, a foreground segmentation mask or depth field may be provided as an additional supervision input with each 2D image. In an embodiment, the foreground segmentation mask or depth field is automatically generated for each 2D image. The constructed 3D model comprises a triangular mesh topology, materials, and environment lighting. The constructed 3D model is represented in a format that can be directly edited and/or rendered by conventional application programs, such as digital content creation (DCC) tools. For example, the constructed 3D model may be represented as a triangular surface mesh (with arbitrary topology), a set of 2D textures representing spatially-varying material parameters, and an environment map. Furthermore, the constructed 3D model may be included in 3D scenes and interacts realistically with other objects.

Abstract: A technique is described for extracting or constructing a three-dimensional (3D) model from multiple two-dimensional (2D) images. In an embodiment, a foreground segmentation mask or depth field may be provided as an additional supervision input with each 2D image. In an embodiment, the foreground segmentation mask or depth field is automatically generated for each 2D image. The constructed 3D model comprises a triangular mesh topology, materials, and environment lighting. The constructed 3D model is represented in a format that can be directly edited and/or rendered by conventional application programs, such as digital content creation (DCC) tools. For example, the constructed 3D model may be represented as a triangular surface mesh (with arbitrary topology), a set of 2D textures representing spatially-varying material parameters, and an environment map. Furthermore, the constructed 3D model may be included in 3D scenes and interacts realistically with other objects.

Abstract: Neural network performance is improved in terms of training speed and/or accuracy by encoding (mapping) inputs to the neural network into a higher dimensional space via a hash function. The input comprises coordinates used to identify a point within a d-dimensional space (e.g., 3D space). The point is quantized and a set of vertex coordinates corresponding to the point are input to a hash function. For example, for d=3, space may be partitioned into axis-aligned voxels of identical size and vertex coordinates of a voxel containing the point are input to the hash function to produce a set of encoded coordinates. The set of encoded coordinates is used to lookup D-dimensional feature vectors in a table of size T that have been learned. The learned feature vectors are filtered (e.g., linearly interpolated, etc.) based on the coordinates of the point to compute a feature vector corresponding to the point.