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

2026-05-14

AI Summary

This work addresses the challenge of image restoration in complex nighttime scenes, where low-light conditions coexist with multiple degradations such as rain and haze, and paired training data are scarce. To this end, we introduce the first nighttime image dataset that jointly captures coupled variations in illumination and diverse degradations. We propose a novel illumination-guided diffusion model that, for the first time, integrates illumination estimation and guidance mechanisms directly into the diffusion architecture to enable end-to-end collaborative restoration. Trained on a combination of synthetic and real-world data, the proposed method significantly enhances restoration quality across various composite degradation scenarios while simultaneously achieving accurate illumination correction and faithful texture detail preservation.

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.

Problem

• night scene restoration
• low-light degradation
• complex degradation
• paired data scarcity
• illumination restoration

Innovation

• illumination-guided diffusion
• complex night scene restoration
• low-light image enhancement
• multi-degradation modeling
• paired nighttime dataset