Aug 2026· International Conference on Computer Vision and Pattern Analysis· Vol 14296, pp. 1429603 - 1429603-8· 0 citations· 19 references
Engineering
TL;DR
This work introduces a Multi-Domain Attention Module (MDAM) to integrate spatial features with frequency-domain global context, and a Dynamic Frequency-domain Fusion Module (DFFM) that employs dynamic filters for detail refinement, noise suppression, and local brightness correction.
Abstract
Existing low-light enhancement methods often suffer from blur, noise, and inconsistent brightness, largely because they overlook frequency-domain characteristics. To address this, we propose the Multi-scale Dynamic Frequency-domain Optimization Network (MDFNet). Specifically, we introduce a Multi-Domain Attention Module (MDAM) to integrate spatial features with frequency-domain global context, and a Dynamic Frequency-domain Fusion Module (DFFM) that employs dynamic filters for detail refinement, noise suppression, and local brightness correction. Furthermore, a learnable fusion mechanism balances high- and low-frequency signals to ensure uniform illumination. Comprehensive experiments demonstrate that MDFNet outperforms state-of-the-art methods in terms of both objective metrics and visual quality.
The proposed AASFNet achieves competitive or leading performance across multiple key metrics under the evaluated experimental settings, yielding the best or second-best PSNR, SSIM, and NIQE values among the compared methods.
Yang Li, Xian-Guo Li, Dan He et al.· Electronics· 0 citations
Low-light image enhancement is challenging due to noise and poor visibility. While diffusion models have shown remarkable generative capabilities, applying them directly to this task in the pixel domain remains problematic. They tend to struggle with the trade-off between global illumination correction and local detail...
Ping-Ping Liu, Jia-Hao Liu, S. Pei et al.· Neural Networks· 0 citations
The Edge-guided Hybrid Enhancement Network (EHENet), an efficient network integrating structural priors and spatial-angular extraction, is proposed, which significantly outperforms state-of-the-art methods in both quality and efficiency.
Hao Wu, Bing-Jie Zhu, Shizheng Li et al.· International Conference on...· 0 citations
The Spatial-Frequency Fusion Network (SFF-Net), which decouples intensity and chroma in HVI space and then learns frequency-aware enhancement with cross-branch compensation, is proposed, which improves SICE, Sony-Total-Dark, and unpaired real image results with only 1.931 M parameters.
Ying-Bo Jia· Conference on Advanced Algor...· 0 citations
A multi-scale detailed information exploration network is proposed that outperforms other state-of-the-art image enhancement approaches in both visual effects and evaluation metrics.
Rain streaks with diverse spatial scales and intensities make single image deraining challenging, often causing residual rain artifacts or the loss of fine details. To address this issue, this paper proposes MSDA-Net (Multi-Scale Degradation-Aware Feature Enhancement Network), a multi-scale degradation -aware feature e...
Jing-Qi Qiao, Tie-Jun Zhang· 2026 7th International Confe...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.