Adaptive Luminance Enhancement and High-Fidelity Color Correction for Low-Light Image Enhancement

It is a challenging task to obtain high-quality images in low-light scenarios. While existing low-light image enhancement methods learn the mapping from low-light to clear images, such a straightforward approach lacks the targeted design for real-world scenarios, hampering their practical utility. As a result, issues such as overexposure and color distortion are likely to arise when processing images in uneven luminance or extreme darkness. To address these issues, we propose an adaptive luminance enhancement and high-fidelity color correction network (LCNet), which adopts a strategy of enhancing luminance first and then correcting color. Specifically, in the adaptive luminance enhancement stage, we design a multi-stage dual attention residual module (MDARM), which incorporates parallel spatial and channel attention mechanisms within residual blocks. This module extracts luminance prior from the low-light image to adaptively enhance luminance, while suppressing overexposure in areas with sufficient luminance. In the high-fidelity color correction stage, we design a progressive multi-scale feature fusion module (PMFFM) that combines progressively stage-wise multi-scale feature fusion with long/short skip connections, enabling thorough interaction between features at different scales across stages. This module extracts and fuses color features with varying receptive fields to ensure accurate and consistent color correction. Furthermore, we introduce a multi-color-space loss to effectively constrain the color correction. These two stages together produce high-quality images with appropriate luminance and high-fidelity color. Extensive experiments on both low-level and high-level tasks demonstrate that our LCNet outperforms state-of-the-art methods and achieves superior performance for low-light image enhancement in real-world scenarios.