Uncertainty-Guided Latent Diffusion Models for Faithful Super Resolution

2026-08-26

AI Summary

本文提出UGDiff方法，通过估计高保真图像的潜在特征重建不确定性来指导扩散过程，以改善感知-失真平衡问题。

Abstract

The perception-distortion trade-off poses a fundamental challenge in single-image super-resolution (SR). Although diffusion-based SR methods excel at generating perceptually realistic images, achieving high fidelity remains a key limitation. Recent advances in diffusion-based SR have shown promise in improving fidelity, but these methods often compromise perceptual quality due to their high reliance on a high-fidelity image. To address this, we introduce UGDiff, a novel diffusion guidance paradigm designed to further improve the perception-distortion balance. In particular, we first estimate the reconstruction uncertainty of the latent features corresponding to a high-fidelity image. This uncertainty is then used to guide the diffusion process to selectively restore high-frequency details in high-uncertainty regions, while preserving fidelity elsewhere. Furthermore, our guidance method adaptively identifies the high-uncertainty regions by considering not only the estimated uncertainty but also the posterior variance of the diffusion sampler at each timestep. This relaxes the reliance on the high-fidelity image in the later stages of sampling, thereby achieving a better perception-distortion balance. Extensive experimental results demonstrate that our method performs favorably against state-of-the-art diffusion-based SR methods.

Problem

• single-image super-resolution
• perception-distortion trade-off
• diffusion-based SR
• fidelity

Innovation

• Uncertainty-Guided
• Latent Diffusion Models
• Perception-Distortion Balance
• High-Frequency Details
• Adaptive Identification