Saved in:
Bibliographic Details
Main Authors: Li, Huaqiu, Hu, Xiaowan, Wang, Haoqian
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2503.14535
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909542211649536
author Li, Huaqiu
Hu, Xiaowan
Wang, Haoqian
author_facet Li, Huaqiu
Hu, Xiaowan
Wang, Haoqian
contents Real-world low-light images often suffer from complex degradations such as local overexposure, low brightness, noise, and uneven illumination. Supervised methods tend to overfit to specific scenarios, while unsupervised methods, though better at generalization, struggle to model these degradations due to the lack of reference images. To address this issue, we propose an interpretable, zero-reference joint denoising and low-light enhancement framework tailored for real-world scenarios. Our method derives a training strategy based on paired sub-images with varying illumination and noise levels, grounded in physical imaging principles and retinex theory. Additionally, we leverage the Discrete Cosine Transform (DCT) to perform frequency domain decomposition in the sRGB space, and introduce an implicit-guided hybrid representation strategy that effectively separates intricate compounded degradations. In the backbone network design, we develop retinal decomposition network guided by implicit degradation representation mechanisms. Extensive experiments demonstrate the superiority of our method. Code will be available at https://github.com/huaqlili/unsupervised-light-enhance-ICLR2025.
format Preprint
id arxiv_https___arxiv_org_abs_2503_14535
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Interpretable Unsupervised Joint Denoising and Enhancement for Real-World low-light Scenarios
Li, Huaqiu
Hu, Xiaowan
Wang, Haoqian
Computer Vision and Pattern Recognition
Artificial Intelligence
Image and Video Processing
Real-world low-light images often suffer from complex degradations such as local overexposure, low brightness, noise, and uneven illumination. Supervised methods tend to overfit to specific scenarios, while unsupervised methods, though better at generalization, struggle to model these degradations due to the lack of reference images. To address this issue, we propose an interpretable, zero-reference joint denoising and low-light enhancement framework tailored for real-world scenarios. Our method derives a training strategy based on paired sub-images with varying illumination and noise levels, grounded in physical imaging principles and retinex theory. Additionally, we leverage the Discrete Cosine Transform (DCT) to perform frequency domain decomposition in the sRGB space, and introduce an implicit-guided hybrid representation strategy that effectively separates intricate compounded degradations. In the backbone network design, we develop retinal decomposition network guided by implicit degradation representation mechanisms. Extensive experiments demonstrate the superiority of our method. Code will be available at https://github.com/huaqlili/unsupervised-light-enhance-ICLR2025.
title Interpretable Unsupervised Joint Denoising and Enhancement for Real-World low-light Scenarios
topic Computer Vision and Pattern Recognition
Artificial Intelligence
Image and Video Processing
url https://arxiv.org/abs/2503.14535