Scene generation using neural radiance fields
AssigneeNVIDIA Corporation
InventorsYue Wang, Jiawei Yang, Boris Ivanovic, Xinshuo Weng, Or Litany, Danfei Xu, Seung Wook Kim, Sanja Fidler, Marco Pavone, Boyi Li, Tong Che
Life of this patent
Estimating the term…
Abstract
Apparatuses, systems, and techniques to generate an image of an environment. In at least one embodiment, one or more neural networks are used to identify one or more static and dynamic features of an environment to be used to generate a representation of the environment.
Claims20
A method of generating one or more images comprising:
- accessing a three-dimensional (3D) representation of an environment;
- determining one or more static features and one or more dynamic features of the 3D representation;
- determining, using the one or more static features, one or more static density values;
- determining, using the one or more dynamic feature, one or more dynamic density values;
- and
- generating the one or more images based on the one or more static density values and the one or more dynamic density values.
A non-transitory computer readable storage medium storing thereon executable instructions that, as a result of being executed by one or more processors of a computer system, cause the computer system to:
- access a three-dimensional (3D) representation of an environment;
- determine one or more static features and one or more dynamic features of the 3D representation;
- determine, using the one or more static features, one or more static density values;
- determine, using the one or more dynamic feature, one or more dynamic density values;
- and
- generate one or more images based on the one or more static density values and the one or more dynamic density values.
A system comprising:
- one or more processors to:
- access a three-dimensional (3D) representation of an environment;
- determine one or more static features and one or more dynamic features of the 3D representation;
- determine, using the one or more static features, one or more static density values;
- determine, using the one or more dynamic feature, one or more dynamic density values;
- and
- generate one or more images based on the one or more static density values and the one or more dynamic density values.
Dependencies are inferred from the claim text.