Brighten-and-Colorize: A Decoupled Network for Customized Low-Light Image Enhancement

TL;DR

This paper introduces BCNet, a decoupled network for low-light image enhancement that separately handles lightness and chrominance, enabling accurate, customizable, and high-quality color enhancement in low-light images.

Contribution

The paper proposes a novel decoupled multi-task network that combines low-light enhancement with image colorization, allowing user-guided customization without sacrificing structural details.

Findings

Achieves state-of-the-art performance on LLIE datasets.

Enables user-controlled color customization in low-light images.

Maintains structural integrity while providing diverse color styles.

Abstract

Low-Light Image Enhancement (LLIE) aims to improve the perceptual quality of an image captured in low-light conditions. Generally, a low-light image can be divided into lightness and chrominance components. Recent advances in this area mainly focus on the refinement of the lightness, while ignoring the role of chrominance. It easily leads to chromatic aberration and, to some extent, limits the diverse applications of chrominance in customized LLIE. In this work, a ``brighten-and-colorize'' network (called BCNet), which introduces image colorization to LLIE, is proposed to address the above issues. BCNet can accomplish LLIE with accurate color and simultaneously enables customized enhancement with varying saturations and color styles based on user preferences. Specifically, BCNet regards LLIE as a multi-task learning problem: brightening and colorization. The brightening sub-task aligns with other conventional LLIE methods to get a well-lit lightness. The colorization sub-task is accomplished by regarding the chrominance of the low-light image as color guidance like the user-guide image colorization. Upon completion of model training, the color guidance (i.e., input low-light chrominance) can be simply manipulated by users to acquire customized results. This customized process is optional and, due to its decoupled nature, does not compromise the structural and detailed information of lightness. Extensive experiments on the commonly used LLIE datasets show that the proposed method achieves both State-Of-The-Art (SOTA) performance and user-friendly customization.