2024/12/21 by Tong Li, Li, Tong, Lizhi Wang +9
Computer Science · #Advanced Vision and Imaging #Artificial intelligence #Computer Vision and Pattern Recognition (cs.CV) #Computer science #Computer vision #FOS: Computer and information sciences #Image (mathematics) #Image Enhancement Techniques #Image and Signal Denoising Methods #Image enhancement #Redundancy (engineering)
paper · pdf · doi:10.48550/arxiv.2412.16459
published in arXiv (Cornell University) (Cornell University)
openalex publication_date 2024/12/21 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/05
Low-light image enhancement (LLIE) is a fundamental task in computational photography, aiming to improve illumination, reduce noise, and enhance the image quality of low-light images. While recent advancements primarily focus on customizing complex neural network models, we have observed significant redundancy in these models, limiting further performance improvement. In this paper, we investigate and rethink the model redundancy for LLIE, identifying parameter harmfulness and parameter uselessness. Inspired by the rethinking, we propose two innovative techniques to mitigate model redundancy while improving the LLIE performance: Attention Dynamic Reallocation (ADR) and Parameter Orthogonal Generation (POG). ADR dynamically reallocates appropriate attention based on original attention, thereby mitigating parameter harmfulness. POG learns orthogonal basis embeddings of parameters and prevents degradation to static parameters, thereby mitigating parameter uselessness. Experiments validate the effectiveness of our techniques. We will release the code to the public.