Patent Leaderboard
USPTO Patent Rankings Data through Dec 31, 2025
Home › Generating depth images utilizing a machine-learning model built from mixed digital image sources and multiple loss function sets

Generating depth images utilizing a machine-learning model built from mixed digital image sources and multiple loss function sets

US Patent 11798180 · Granted Oct 24, 2023

Estimated economic value: $203,651,000 ⓘ

Assignee

Inventors

View full patent text on Google Patents →

More Patents by These Inventors

Diffusion models having continuous scaling through patch-wise image generation2025
Object class inpainting in digital images utilizing class-specific inpainting ne2025
Image and object inpainting with diffusion models2025
Power connector with increased plugging force and improved heat dissipation perf2025
Transformer for efficient image segmentation2025
Generating soft object shadows for general shadow receivers within digital image2025
Generating and providing a panoptic inpainting interface for generating and modi2025
Iteratively modifying inpainted digital images based on changes to panoptic segm2025
Utilizing machine learning models to generate refined depth maps with segmentati2025
Utilizing machine learning models to generate refined depth maps with segmentati2025
Utilizing machine learning models to generate refined depth maps with segmentati2025
Learning parameters for neural networks using a semantic discriminator and an ob2025