Nvidia patents method to turn camera views into top-down maps for machines
Nvidia describes a system that takes data from multiple camera angles and converts it into a single top-down map, known as a bird's-eye view. It uses machine learning models to adjust the data so it fits a grid, helping machines understand the layout of their surroundings from above.
In the filing’s own words
In various examples, feature values corresponding to a plurality of views are transformed into feature values of a shared orientation or perspective to generate a feature map-such as a Bird's-Eye-View (BEV), top-down, orthogonally projected, and/or other shared perspective feature map type. Feature values corresponding to a region of a view may be transformed into feature values using a neural network. The feature values may be assigned to bins of a grid and values assigned to at least one same bin may be combined to generate one or more feature values for the feature map. To assign the transformed features to the bins, one or more portions of a view may be projected into one or more bins using polynomial curves. Radial and/or angular bins may be used to represent the environment for the feature map.
What exactly they claim (claim 1)
1. A system comprising: one or more sensors used to obtain feature data corresponding to one or more views of an environment, wherein the system causes a machine to perform, using one or more first machine learning models (MLMs) and based at least on a bird's-eye view (BEV) representation of the environment, one or more operations for a machine, the BEV representation determined based at least on: selecting, from the feature data, a region of feature values that corresponds to a subset of the one or more views based at least on spatial relationships among the feature values within the one or more views; modifying, using the one or more first MLMs or one or more second MLMs, the feature values of the region to correspond to one or more dimensions of a BEV of the environment based at least on the spatial relationships; and mapping the modified feature values to one or more positions within the BEV representation of the environment.
Facts
- Company
- Nvidia (NVIDIA Corporation)
- Official title
- SCENE PERCEPTION
- Publication number
- US20260260465A1
- Application number
- 19655428
- Filed
- Apr 22, 2026
- Published
- Sep 3, 2026
- Inventors
- 8
- Claims
- 20
Classified under
G06V 10/7715 Physics & computingG06V 10/82 Physics & computingG06V 20/56 Physics & computingMore from Nvidia in AI & software
- Nvidia patents AI coach that analyzes your gameplay to suggest strategies Oct 13, 2026
- Nvidia patents AI system that writes and voices character conversations Sep 10, 2026
- Nvidia patents system that uses AI to find bugs in game videos Sep 17, 2026
- Nvidia patents AI method to make digital characters move realistically Sep 8, 2026
- Nvidia patents AI system that builds image generators from text prompts Sep 15, 2026
Summaries are simplified from the filing’s own abstract and first claim. A patent filing is not a product announcement.
Patent data and drawings: U.S. Patent and Trademark Office (USPTO). Nebula is not affiliated with or endorsed by the USPTO.