Lightweight network improves brightness and color in low light images
IDM-Net: A Lightweight Illumination-Decoupled Modulation Network for Low-Light Image Enhancement
Computer Vision and Pattern Recognition
Summary
Photos taken in low light often look dark and have weird colors. The authors introduce IDM-Net, a small and fast computer program that uses two different ways to understand an image: one to see shapes and colors, and another to understand lighting. By combining these, their method brightens photos while keeping the colors looking natural and fixing small flaws in the image. Their tests show this approach works well compared to similar lightweight methods.
What this means in practice
- •For mobile app developers: Enhance photos taken in low light on smartphones efficiently without using heavy computing resources.
- •For security camera operators: Improve visibility and color accuracy in surveillance footage recorded under poor lighting conditions.
Authors
Cheng-Yen Hsiao, Jing-Ming Guo
Abstract
Low-light image enhancement (LLIE) remains challenging for lightweight models because illumination restoration and color fidelity are difficult to optimize simultaneously in the RGB color space. Although recent color-decoupled methods separate luminance and chrominance representations, they primarily optimize luminance as an enhancement target, leaving its potential as an explicit guidance prior largely unexplored during feature reconstruction. To address this limitation, we propose IDM-Net, a lightweight Illumination-Decoupled Modulation Network for low-light image enhancement. IDM-Net adopts a dual-encoder architecture consisting of a structure encoder that extracts multi-scale appearance features from the RGB image and a lightweight illumination encoder that learns illumination priors from the decoupled luminance (Y) channel. To effectively exploit these priors, we introduce an Illumination-Guided Modulation (IGM) module that injects multi-scale illumination cues into the decoder through spatially adaptive affine modulation, enabling accurate brightness restoration while preserving natural color consistency. Furthermore, we design a lightweight Feature Refinement Block (FRB) to progressively suppress degradation artifacts and recover fine-grained image details during reconstruction. Extensive experiments on multiple standard low-light image enhancement benchmarks demonstrate that IDM-Net achieves competitive performance among lightweight LLIE methods while maintaining an excellent balance between restoration quality and computational efficiency.