A Collaborative Network of Mamba and CNN for Lightweight Image Super-Resolution
IEEE Transactions on Consumer Electronics · 2025-05 · 71 (2) · 3591-3604
DOI: 10.1109/tce.2025.3572477 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Consumer Electronics, 2025-05. Verfasst von Xin Wang und 5 weiteren Autor:innen. Die Arbeit wurde bisher 14-mal zitiert (Crossref) und nennt 76 Literaturangaben. Gefördert von: Establishment of Key Laboratory of Shenzhen Science and Technology Innovation Committee, Shenzhen Science and Technology Innovation Committee, Natural Scientific Foundation of China.
Abstract (Originalsprache)
Single image super-resolution (SR) can recover high-resolution images from the corresponding low-resolution counterparts, which meets the application demands of consumer electronics, such as improving the visual experience of smart televisions (TVs) and virtual reality (VR) devices. Although deep learning-based SR methods have recently gained promising success, most existing approaches typically stack numerous network layers, which significantly increases the model complexity and hinders the deployment on electronics with limited computational capability. To tackle this problem, we propose a collaborative network of Mamba and CNN (CNMC) for lightweight image super-resolution. CNMC is mainly composed of multiple collaborative units of Mamba and CNN (CUMCs), which leverage the complementary advantages of Mamba and CNN to extract deep features beneficial for reconstruction. Specifically, CUMC introduces Mamba which enjoys the global receptive field and linear complexity, to perform long-range dependency modeling. Additionally, it employs CNN with the significant inductive bias to facilitate the local information interaction and compensation. The collaboration between Mamba and CNN effectively exploits both non-local and local priors, ensuring a comprehensive enhancement of deep features. Furthermore, a multi-scale spatial refinement attention (MSSRA) is developed in CUMC, to modulate channel-wise weights of features using a spatial fine-grained manner at different scales and then aggregate these cross-scale features, thereby distilling important information and restoring more precise details. Extensive quantitative and qualitative experiments demonstrate the superiority of our CNMC over other state-of-the-art lightweight SR methods. Most importantly, compared to the recent Transformer-based methods NGswin and HSSRNet, our CNMC achieves PSNR improvements of 0.21 dB and 0.32 dB for $\times 2$ SR on Urban100 dataset. Code is available at https://github.com/HITXinWang/CNMC.
Förderung
- Establishment of Key Laboratory of Shenzhen Science and Technology Innovation Committee
- Shenzhen Science and Technology Innovation Committee
- Natural Scientific Foundation of China
- Shenzhen Science and Technology Program
Zitieren
APA
Wang, X., Li, J., Li, J., Wang, S., Yan, L., & Xu, Y. (2025). A Collaborative Network of Mamba and CNN for Lightweight Image Super-Resolution. IEEE Transactions on Consumer Electronics, 71(2), 3591-3604. https://doi.org/10.1109/tce.2025.3572477
Vancouver
Wang X, Li J, Li J, Wang S, Yan L, Xu Y. A Collaborative Network of Mamba and CNN for Lightweight Image Super-Resolution. IEEE Transactions on Consumer Electronics. 2025;71(2):3591-3604. doi:10.1109/tce.2025.3572477
BibTeX
@article{Wang2025,
author = {Wang, Xin and Li, Jinxing and Li, Jinkai and Wang, Shiqi and Yan, Liang and Xu, Yong},
title = {A Collaborative Network of Mamba and CNN for Lightweight Image Super-Resolution},
journal = {IEEE Transactions on Consumer Electronics},
year = {2025},
volume = {71},
number = {2},
pages = {3591--3604},
doi = {10.1109/tce.2025.3572477}
}
EUVIMED