Patent · US Active

Utilizing voxel feature transformations for deep novel view synthesis

US11393158B2 · kind B2 · utility

0Cited by
1References
20Claims
0Family size

Assignee

Inventors

Key dates

Filing dateApr 2, 2020
Grant dateJul 19, 2022
Priority date
Expiry dateAug 14, 2040

Classification

  • Technology area (CPC G)Physics
  • CPC primaryG06T2207/20084
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

Abstract

Systems, methods, and non-transitory computer-readable media are disclosed for utilizing an encoder-decoder architecture to learn a volumetric 3D representation of an object using digital images of the object from multiple viewpoints to render novel views of the object. For instance, the disclosed systems can utilize patch-based image feature extraction to extract lifted feature representations from images corresponding to different viewpoints of an object. Furthermore, the disclosed systems can model view-dependent transformed feature representations using learned transformation kernels. In addition, the disclosed systems can recurrently and concurrently aggregate the transformed feature representations to generate a 3D voxel representation of the object. Furthermore, the disclosed systems can sample frustum features using the 3D voxel representation and transformation kernels. Then, the disclosed systems can utilize a patch-based neural rendering approach to render images from frustum feature patches to display a view of the object from various viewpoints.

Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.