Scaling Up to Excellence: Practicing Model Scaling for Photo-Realistic Image Restoration In the Wild

arXiv:2401.13627v2 Announce Type: replace
Abstract: We introduce SUPIR (Scaling-UP Image Restoration), a groundbreaking image restoration method that harnesses generative prior and the power of model scaling up. Leveraging multi-modal techniques and advanced generative prior, SUPIR marks a significant advance in intelligent and realistic image restoration. As a pivotal catalyst within SUPIR, model scaling dramatically enhances its capabilities and demonstrates new potential for image restoration. We collect a dataset comprising 20 million high-resolution, high-quality images for model training, each enriched with …

abstract advance advanced arxiv cs.cv generative groundbreaking image image restoration intelligent marks modal model scaling multi-modal photo power prior scaling scaling up type