Robust Low-light Scene Restoration via Illumination Transition

TL;DR

This paper introduces RoSe, a novel framework for synthesizing normal-light views from low-light multiview images by modeling illuminance transition in 3D space, effectively denoising and maintaining multiview consistency.

Contribution

It formulates low-light scene restoration as an illuminance transition estimation in 3D, leveraging low-rank properties for improved denoising and multiview consistency.

Findings

Outperforms state-of-the-art models in rendering quality

Achieves superior multiview consistency

Effectively denoises low-light images without complex noise modeling

Abstract

Synthesizing normal-light novel views from low-light multiview images is an important yet challenging task, given the low visibility and high ISO noise present in the input images. Existing low-light enhancement methods often struggle to effectively preprocess such low-light inputs, as they fail to consider correlations among multiple views. Although other state-of-the-art methods have introduced illumination-related components offering alternative solutions to the problem, they often result in drawbacks such as color distortions and artifacts, and they provide limited denoising effectiveness. In this paper, we propose a novel Robust Low-light Scene Restoration framework (RoSe), which enables effective synthesis of novel views in normal lighting conditions from low-light multiview image inputs, by formulating the task as an illuminance transition estimation problem in 3D space, conceptualizing it as a specialized rendering task. This multiview-consistent illuminance transition field establishes a robust connection between low-light and normal-light conditions. By further exploiting the inherent low-rank property of illumination to constrain the transition representation, we achieve more effective denoising without complex 2D techniques or explicit noise modeling. To implement RoSe, we design a concise dual-branch architecture and introduce a low-rank denoising module. Experiments demonstrate that RoSe significantly outperforms state-of-the-art models in both rendering quality and multiview consistency on standard benchmarks. The codes and data are available at https://pegasus2004.github.io/RoSe.