Pyramid Diffusion Models For Low-light Image Enhancement

TL;DR

This paper introduces PyDiff, a pyramid diffusion model for low-light image enhancement that improves speed and quality by progressively increasing resolution and correcting global degradation, outperforming existing methods.

Contribution

PyDiff is a novel pyramid diffusion approach that accelerates diffusion sampling and reduces global degradation in low-light image enhancement tasks.

Findings

PyDiff achieves superior performance on benchmark datasets.

PyDiff is significantly faster than traditional diffusion models.

PyDiff generalizes well to unseen noise and illumination conditions.

Abstract

Recovering noise-covered details from low-light images is challenging, and the results given by previous methods leave room for improvement. Recent diffusion models show realistic and detailed image generation through a sequence of denoising refinements and motivate us to introduce them to low-light image enhancement for recovering realistic details. However, we found two problems when doing this, i.e., 1) diffusion models keep constant resolution in one reverse process, which limits the speed; 2) diffusion models sometimes result in global degradation (e.g., RGB shift). To address the above problems, this paper proposes a Pyramid Diffusion model (PyDiff) for low-light image enhancement. PyDiff uses a novel pyramid diffusion method to perform sampling in a pyramid resolution style (i.e., progressively increasing resolution in one reverse process). Pyramid diffusion makes PyDiff much faster than vanilla diffusion models and introduces no performance degradation. Furthermore, PyDiff uses a global corrector to alleviate the global degradation that may occur in the reverse process, significantly improving the performance and making the training of diffusion models easier with little additional computational consumption. Extensive experiments on popular benchmarks show that PyDiff achieves superior performance and efficiency. Moreover, PyDiff can generalize well to unseen noise and illumination distributions.