Patent Leaderboard
USPTO Patent Rankings Data through Dec 31, 2025
Home › Systems and methods for training models to predict dense correspondences in images using geodesic distances

Systems and methods for training models to predict dense correspondences in images using geodesic distances

US Patent 11954899 · Granted Apr 9, 2024

Estimated economic value: $129,498,000 ⓘ

Assignee

Inventors

View full patent text on Google Patents →

More Patents by These Inventors

Volumetric performance capture with neural rendering2025
Volumetric performance capture with neural rendering2025
Volumetric performance capture with neural rendering2025
Systems and methods for compression of three-dimensional volumetric representati2025
Systems and methods for compression of three-dimensional volumetric representati2025
Systems and methods for compression of three-dimensional volumetric representati2025
Systems and methods for compression of three-dimensional volumetric representati2025
Foveated images with adaptive exposure2025
Enhanced photo relighting based on machine learning models2025
Enhanced photo relighting based on machine learning models2025
Enhanced photo relighting based on machine learning models2025
Joint depth prediction from dual-cameras and dual-pixels2025