ITRE: Low-light image enhancement based on illumination transmission ratio estimation

Abstract

Noise, artifacts, and over-exposure are substantial challenges in the field of low-light image enhancement. Existing methods often struggle to address these issues simultaneously. In this paper, we propose a method that is based on Illumination Transmission Ratio Estimation (ITRE) to handle the challenges at the same time. Specifically, we assume that there must exist a pixel which is least disturbed by low light for pixels of each color cluster. First, we cluster the pixels on the RGB color space to find the Illumination Transmission Ratio (ITR) matrix of the whole image, which determines that noise is not over-amplified easily. Next, we consider the ITR of the image as the initial illumination transmission map to construct a base model for refining transmission map, which prevents artifacts. In addition, we design an over-exposure module that captures the fundamental characteristics of pixel over-exposure and seamlessly integrates it into the base model. Finally, there is a possibility of weak enhancement when the interclass distance of pixels with the same color is too small. To counteract this, we design an Robust-Guard (RG) module that safeguards the robustness of the image enhancement process. Extensive experiments demonstrate the superiority of the proposed method over state-of-the-art methods in terms of visual quality and quantitative metrics. Our code is available at https://github.com/wangyuro/ITRE.