Patent Leaderboard
USPTO Patent Rankings Data through Dec 31, 2025
Home › Retouching digital images utilizing layer specific deep-learning neural networks

Retouching digital images utilizing layer specific deep-learning neural networks

US Patent 12112456 · Granted Oct 8, 2024

Estimated economic value: $209,514,000 ⓘ

Assignee

Inventors

View full patent text on Google Patents →

More Patents by These Inventors

Object class inpainting in digital images utilizing class-specific inpainting ne2025
Image and object inpainting with diffusion models2025
Supervised learning techniques for encoder training2025
Generating and providing a panoptic inpainting interface for generating and modi2025
Iteratively modifying inpainted digital images based on changes to panoptic segm2025
Learning parameters for neural networks using a semantic discriminator and an ob2025
Generating digital images utilizing high-resolution sparse attention and semanti2025
Human inpainting utilizing a segmentation branch for generating an infill segmen2025
Multi-scale output techniques for generative adversarial networks2025
Utilizing cross-attention guidance to preserve content in diffusion-based image 2025
Direct regression encoder architecture and training2025
Diverse image inpainting using contrastive learning2025