Patent Leaderboard
USPTO Patent Rankings Data through Dec 31, 2025
Home › Modifying neural networks for synthetic conditional digital content generation utilizing contrastive perceptual loss

Modifying neural networks for synthetic conditional digital content generation utilizing contrastive perceptual loss

US Patent 11514632 · Granted Nov 29, 2022

Estimated economic value: $154,084,000 ⓘ

Assignee

Inventors

View full patent text on Google Patents →

More Patents by These Inventors

Generation using depth-conditioned autoencoder2025
Diffusion models having continuous scaling through patch-wise image generation2025
Training an artificial intelligence model based on soft information2025
Semantic image fill at high resolutions2025
Semantic image fill at high resolutions2025
Supervised learning techniques for encoder training2025
Preset style transfer2025
Layout extraction system for regional annotation of images2025
Method for diagnosing ovarian cancer through microbial metagenome analysis2025
Identity preserved controllable facial image manipulation2025
Self-supervised audio-visual learning for correlating music and video2025
Multi-scale output techniques for generative adversarial networks2025