After the Party: Navigating the Mapping From Color to Ambient Lighting

TL;DR

This paper introduces CL3AN, a large-scale dataset and a novel learning framework inspired by the Retinex model, to improve image restoration under complex colored lighting conditions, addressing limitations of existing methods.

Contribution

The paper presents the first high-resolution dataset for multi-colored lighting image restoration and a new learning approach that effectively disentangles illumination from reflectance.

Findings

Improved robustness under non-homogeneous colored lighting

Enhanced preservation of material-specific reflectance details

Competitive computational efficiency

Abstract

Illumination in practical scenarios is inherently complex, involving colored light sources, occlusions, and diverse material interactions that produce intricate reflectance and shading effects. However, existing methods often oversimplify this challenge by assuming a single light source or uniform, white-balanced lighting, leaving many of these complexities unaddressed. In this paper, we introduce CL3AN, the first large-scale, high-resolution dataset of its kind designed to facilitate the restoration of images captured under multiple Colored Light sources to their Ambient-Normalized counterparts. Through benchmarking, we find that leading approaches often produce artifacts, such as illumination inconsistencies, texture leakage, and color distortion, primarily due to their limited ability to precisely disentangle illumination from reflectance. Motivated by this insight, we achieve such a desired decomposition through a novel learning framework that leverages explicit chromaticity-luminance components guidance, drawing inspiration from the principles of the Retinex model. Extensive evaluations on existing benchmarks and our dataset demonstrate the effectiveness of our approach, showcasing enhanced robustness under non-homogeneous color lighting and material-specific reflectance variations, all while maintaining a highly competitive computational cost. The benchmark, codes, and models are available at www.github.com/fvasluianu97/RLN2.