Multi-Domain Multi-Scale Diffusion Model for Low-Light Image Enhancement
Kai Shang, Mingwen Shao, Chao Wang, Yuanshuo Cheng, Shuigen Wang
Abstract
Diffusion models have achieved remarkable progress in lowlight image enhancement. However, there remain two practical limitations: (1) existing methods mainly focus on the spatial domain for the diffusion process, while neglecting the essential features in the frequency domain; (2) conventional patch-based sampling strategy inevitably leads to severe checkerboard artifacts due to the uneven overlapping. To address these limitations in one go, we propose a Multi-Domain Multi-Scale (MDMS) diffusion model for low-light image enhancement. In particular, we introduce a spatialfrequency fusion module to seamlessly integrates spatial and frequency information. By leveraging the Multi-Domain Learning (MDL) paradigm, our proposed model is endowed with the capability to adaptively facilitate noise distribution learning, thereby enhancing the quality of the generated images. Meanwhile, we propose a Multi-Scale Sampling (MSS) strategy that follows a divide-ensemble manner by merging the restored patches under different resolutions. Such a multi-scale learning paradigm explicitly derives patch information from different granularities, thus leading to smoother boundaries. Furthermore, we empirically adopt the Bright Channel Prior (BCP) which indicates natural statistical regularity as an additional restoration guidance. Experimental results on LOL and LOLv2 datasets demonstrate that our method achieves state-of-the-art performance for the low-light image enhancement task. Codes are available at https://github.com/Oliiveralien/MDMS.
Ask Lune
Know this paper in minutes, not an afternoon.
Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.
3 top-tier papers have cited it since. Know what they found before your reviewers do.
Lune can draw on
the full paper · the top-tier papers that cite it · related work
Free to start. No credit card required.
Lineage
- High-Resolution Image Synthesis with Latent Diffusion Models cites Diffusion Models Beat GANs on Image Synthesis
- Adapting Text-to-Image Generation with Feature Difference Instruction for Generic Image Restoration cites High-Resolution Image Synthesis with Latent Diffusion Models
- Adapting Text-to-Image Generation with Feature Difference Instruction for Generic Image Restoration cites URetinex-Net: Retinex-based Deep Unfolding Network for Low-light Image Enhancement
- TPGDiff : Hierarchical Triple-Prior Guided Diffusion for Image Restoration cites Adapting Text-to-Image Generation with Feature Difference Instruction for Generic Image Restoration
- Directly Denoising Diffusion Models cites High-Resolution Image Synthesis with Latent Diffusion Models
- Directly Denoising Diffusion Models cites Diffusion Models Beat GANs on Image Synthesis
- Physical-aware Neural Radiance Fields for Efficient Exposure Correction cites Toward Fast, Flexible, and Robust Low-Light Image Enhancement
Cited by top-tier papers3
- TPGDiff : Hierarchical Triple-Prior Guided Diffusion for Image RestorationYanjie Tu, Qingsen Yan, Axi Niu, Jiacong TangICML 2026 · 2 citations
- Physical-aware Neural Radiance Fields for Efficient Exposure CorrectionKai Xu, Mingwen Shao, Yuanjian Qiao, Yan WangAAAI 2025 · 2 citations
- Adapting Text-to-Image Generation with Feature Difference Instruction for Generic Image RestorationChao Wang, Hehe Fan, Huichen Yang, Sarvnaz Karimi et al.CVPR 2025
Builds on13
- Diffusion Models Beat GANs on Image SynthesisPrafulla Dhariwal, Alexander Quinn NicholNeurIPS 2021 · 13,211 citations
- High-Resolution Image Synthesis with Latent Diffusion ModelsRobin Rombach, Andreas Blattmann, Dominik Lorenz, Patrick Esser et al.CVPR 2022 · 13,123 citations
- Directly Denoising Diffusion ModelsDan Zhang, Jingjing Wang, Feng LuoICML 2024 · 11,724 citations
- Toward Fast, Flexible, and Robust Low-Light Image EnhancementLong Ma, Tengyu Ma, Risheng Liu, Xin Fan et al.CVPR 2022 · 928 citations
- URetinex-Net: Retinex-based Deep Unfolding Network for Low-light Image EnhancementWenhui Wu, Jian Weng, Pingping Zhang, Xu Wang et al.CVPR 2022 · 695 citations
Related papers
- PGDM: Physics-Guided Noise-Free Diffusion Model Based on Point Spread Function for Light-Scattering Removal in Unpaired Biomedical ImagesJinze Zhao, Keyi Han, Qiushi Huang, Jie Tian, Zhenhua HuCVPR Findings 2026
- Adaptively Learning Low-high Frequency Information Integration for Pan-sharpeningMan Zhou, Jie Huang, Chongyi Li, Hu Yu et al.ACM MM 2022 · 44 citations
- Illumination Distribution Prior for Low-light Image EnhancementChao Wang, Yang Zhou, Liangtian He, Fenglai Lin et al.ACM MM 2024 · 3 citations
- Frequency Domain-Based Diffusion Model for Unpaired Image DehazingChengxu Liu, Lu Qi, Jinshan Pan, Xueming Qian et al.ICCV 2025 · 13 citations
- Generative Diffusion Prior for Unified Image Restoration and EnhancementBen Fei, Zhaoyang Lyu, Liang Pan, Junzhe Zhang et al.CVPR 2023
