MambaDPF-Net: A Dual-Path Fusion Network with Selective State Space Modeling for Robust Low-Light Image Enhancement
Open Access
- 19 November 2025
- journal article
- research article
- Published by MDPI AG in Electronics
- Vol. 14 (22) , 4533
Abstract
Low-light images commonly suffer from insufficient contrast, noise accumulation, and colour shifts, which impair human perception and subsequent visual tasks. We propose MambaDPF-Net—a dual-path fusion framework based on the retinal effect, adhering to a ‘decoupling–denoising–coupling’ paradigm while incorporating sharpening priors for texture stabilisation. Specifically, the decoupling branch estimates illumination and reflectance through dual-scale feature aggregation with physically interpretable constraints; the denoising branch primarily performs noise reduction in the reflectance domain, employing an illumination-aware modulation mechanism to prevent excessive smoothing in low-SNR regions; the coupling branch utilises a selective state space module (Mamba) to adaptively fuse spatio-temporal representations, achieving non-local interactions and cross-region long-range dependency modelling with near-linear complexity. Extensive experiments on public datasets demonstrate that this method achieves state-of-the-art performance on metrics such as PSNR and SSIM, excels in non-reference evaluations, and produces natural colours with enhanced details. This validates the proposed approach’s effectiveness and robustness.Keywords
This publication has 30 references indexed in Scilit:
- Meta-DNET-UPI: Efficient underwater polarization imaging combining deformable convolutional networks and meta-learningOptics & Laser Technology, 2025
- Efficient low-light image enhancement with model parameters scaled down to 0.02MInternational Journal of Machine Learning and Cybernetics, 2023
- Advanced RetinexNet: A fully convolutional network for low-light image enhancementSignal Processing: Image Communication, 2022
- R2RNet: Low-light image enhancement via Real-low to Real-normal NetworkJournal of Visual Communication and Image Representation, 2022
- LE-GAN: Unsupervised low-light image enhancement network using attention module and identity invariant lossKnowledge-Based Systems, 2022
- Fuzzy Gray Level Difference Histogram Equalization for Medical Image EnhancementJournal of Medical Systems, 2020
- LLNet: A deep autoencoder approach to natural low-light image enhancementPattern Recognition, 2017
- LIME: Low-Light Image Enhancement via Illumination Map EstimationIEEE Transactions on Image Processing, 2016
- A fusion-based enhancing method for weakly illuminated imagesSignal Processing, 2016
- A multiscale retinex for bridging the gap between color images and the human observation of scenesIEEE Transactions on Image Processing, 1997