23 September 2024 in ACM Transactions on Multimedia Computing, Communications, and Applications
Low-Light Image Enhancement (LLIE) presents challenges due to texture information loss and uneven illumination, which can distort feature distribution and reduce the quality of the enhanced images. However, current deep learning methods for LLIE only use supervised information from clear images to extract low-light image features, while disregarding the negative information in low-light images (i.e., low illumination and noise). To address these challenges, we propose a novel LLIE method, LACR-VAE, by leveraging the negative information and considering the uneven illumination. In particular, a Light-Aware Contrastive Regularization (LACR) based on contrastive learning is designed to exploit information from both clear and low-light images. The LACR aims to align latent variables of enhanced images with clear images, away from those of low-light images. This allows the method to prioritize essential elements for LLIE and minimize noise and lighting variations. Furthermore, considering the uneven illumination with diverse region sizes and shapes, a Region-CAlibrated Module (RCAM) is present to learn local and global illumination relations among image regions, and an Attention-guided Multi-Scale Module (AMSM) is designed to extract multi-scale features that improve the model’s representation capability. Extensive experiments show that our method achieves superior performance than previous works. Specifically, our method yields a significant enhancement in the National Aeronautics and Space Administration (NASA) testset, achieving an improvement of at least 0.99 in PSNR and 0.0409 in SSIM. Codes and datasets are available at https://github.com/csxuwu/LACR-VAE .
6 October 2023 in IEEE Transactions on Emerging Topics in Computational Intelligence
Low-light image enhancement aims to improve the illumination intensity while restoring color information. Despite recent advancements using deep learning methods, they still struggle with over or under-exposure in complex lighting scenes and poor color recovery in dark regions. To address these drawbacks, we propose a novel pipeline (called LRCR-Net) to perform Light Restoration and Color Refinement in a coarse-to-fine manner. In the coarse step, we focus on improving the illumination adaptively while avoiding inappropriate enhancement in the brighter or darker regions. This is achieved by introducing a region-calibrated residual block (RCRB) that balances local and global dependencies among different image regions. In the fine step, we aim to retouch the color of the images enhanced in the coarse step. To achieve this goal, we propose learnable image processing operators (LIPOs), including contrast and saturation operators, to refine the color according to the input images' color and contrast information. The final result is an image with proper illumination and rich color. Experiments on four benchmark datasets (NASA, LIME, MEF, and NPE) show that our model outperforms state-of-the-art methods.
30 May 2025 in Engineering Applications of Artificial Intelligence
27 February 2026 in IEEE Transactions on Multimedia
Low-light image enhancement (LLIE) aims to improve illumination while preserving high-quality color and texture. However, existing methods often fail to extract reliable feature representations due to severely degraded pixel-level information under low-light conditions, resulting in poor texture restoration, color inconsistency, and artifact. To address these challenges, we propose LightQANet, a novel framework that introduces quantized and adaptive feature learning for low-light enhancement, aiming to achieve consistent and robust image quality across diverse lighting conditions. From the static modeling perspective, we design a Light Quantization Module (LQM) to explicitly extract and quantify illumination-related factors from image features. By enforcing structured light factor learning, LQM enhances the extraction of light-invariant representations and mitigates feature inconsistency across varying illumination levels. From the dynamic adaptation perspective, we introduce a Light-Aware Prompt Module (LAPM), which encodes illumination priors into learnable prompts to dynamically guide the feature learning process. LAPM enables the model to flexibly adapt to complex and continuously changing lighting conditions, further improving image enhancement. Extensive experiments on multiple low-light datasets demonstrate that our method achieves state-of-the-art performance, delivering superior qualitative and quantitative results across various challenging lighting scenarios.
3 October 2022 in Multimedia Tools and Applications