IG-Diff: Complex Night Scene Restoration with Illumination-Guided Diffusion Model

TL;DR

This paper introduces IG-Diff, a diffusion model with illumination guidance, designed to restore complex night scenes by handling multiple degradations simultaneously.

Contribution

It presents a new dataset simulating nighttime degradations and a diffusion-based model that effectively restores complex low-light scenes with multiple impairments.

Findings

The model preserves texture fidelity in challenging low-light conditions.

The dataset enables training models on complex nighttime degradations.

The approach outperforms existing methods in complex night scene restoration.

Abstract

In nighttime circumstances, it is challenging for individuals and machines to perceive their surroundings. While prevailing image restoration methods adeptly handle singular forms of degradation, they falter when confronted with intricate nocturnal scenes, such as the concurrent presence of weather and low-light conditions. Compounding this challenge, the lack of paired data that encapsulates the coexistence of low-light situations and other forms of degradation hinders the development of a comprehensive end-to-end solution. In this work, we contribute complex nighttime scene datasets that simulate both illumination degradation and other forms of deterioration. To address the complexity of night degradation, we propose an integration of an illumination-guided module embedded in the diffusion model to guide the illumination restoration process. Our model can preserve texture fidelity while contending with the adversities posed by various degradation in low-light scenarios.