Patent Leaderboard
USPTO Patent Rankings Data through Dec 31, 2025
Home › Extracting attributes from arbitrary digital images utilizing a multi-attribute contrastive classification neural network

Extracting attributes from arbitrary digital images utilizing a multi-attribute contrastive classification neural network

US Patent 12136250 · Granted Nov 5, 2024

Estimated economic value: $196,740,000 ⓘ

Assignee

Inventors

View full patent text on Google Patents →

More Patents by These Inventors

Panoptically guided inpainting utilizing a panoptic inpainting neural network2025
Modifying digital images via perspective-aware object move2025
Recovering gamut color loss utilizing lightweight neural networks2025
Moving objects casting a shadow and generating proxy shadows within a digital im2025
Debiasing image to image translation models2025
Detecting shadows and corresponding objects in digital images2025
Texture-preserving shadow removal in digital images utilizing generating inpaint2025
Methods and systems for generating a semantic computation graph for understandin2025
Methods and systems for generating a semantic computation graph for understandin2025
Object class inpainting in digital images utilizing class-specific inpainting ne2025
Object class inpainting in digital images utilizing class-specific inpainting ne2025
Image and object inpainting with diffusion models2025