Zero-Shot Low Light Image Enhancement with Diffusion Prior

TL;DR

This paper introduces a zero-shot low-light image enhancement method using a pre-trained diffusion prior, achieving superior results without training or fine-tuning, and also performs well on auto white balance tasks.

Contribution

The proposed approach leverages a pre-trained diffusion prior for zero-shot low-light image enhancement, eliminating the need for optimization, training, or hyperparameter tuning.

Findings

Outperforms state-of-the-art methods on established datasets.

Enhances color accuracy and corrects chromatic deviations.

Achieves state-of-the-art performance in auto white balance without modifications.

Abstract

In this paper, we present a simple yet highly effective "free lunch" solution for low-light image enhancement (LLIE), which aims to restore low-light images as if acquired in well-illuminated environments. Our method necessitates no optimization, training, fine-tuning, text conditioning, or hyperparameter adjustments, yet it consistently reconstructs low-light images with superior fidelity. Specifically, we leverage a pre-trained text-to-image diffusion prior, learned from training on a large collection of natural images, and the features present in the model itself to guide the inference, in contrast to existing methods that depend on customized constraints. Comprehensive quantitative evaluations demonstrate that our approach outperforms SOTA methods on established datasets, while qualitative analyses indicate enhanced color accuracy and the rectification of subtle chromatic deviations. Furthermore, additional experiments reveal that our method, without any modifications, achieves SOTA-comparable performance in the auto white balance (AWB) task.