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

TL;DR

SUPIR is a novel image restoration method that combines generative priors, model scaling, and multi-modal techniques to achieve photo-realistic results guided by text prompts, with improved perceptual quality and versatility.

Contribution

The paper introduces SUPIR, a scalable image restoration framework that integrates generative priors, textual guidance, and negative prompts, advancing the state-of-the-art in realistic image restoration.

Findings

SUPIR achieves superior restoration quality compared to existing methods.

Text-guided restoration allows flexible manipulation of images.

Negative prompts enhance perceptual quality and detail fidelity.

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 descriptive text annotations. SUPIR provides the capability to restore images guided by textual prompts, broadening its application scope and potential. Moreover, we introduce negative-quality prompts to further improve perceptual quality. We also develop a restoration-guided sampling method to suppress the fidelity issue encountered in generative-based restoration. Experiments demonstrate SUPIR's exceptional restoration effects and its novel capacity to manipulate restoration through textual prompts.