VMamba-ADD: A Dual-Branch Adversarial Diffusion Distillation Network for Efficient Blind Super-Resolution
Applied Sciences · 10.11.2026 · 16 (22) · 11097
DOI: 10.3390/app162211097 ↗Kurz gefasst
Fachartikel in der Zeitschrift Applied Sciences, online erschienen am 10.11.2026. Verfasst von Tongyan Liu und 5 weiteren Autor:innen. Die Arbeit nennt 30 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Blind super-resolution aims to reconstruct high-resolution images from low-resolution inputs affected by complex and unknown degradations. Although adversarial diffusion distillation (ADD) has achieved significant improvements in inference speed, its aggressive distillation process inevitably weakens the modelling of long-range structures, leading to structural hallucinations and distorted details in complex scenes. To address these limitations, this study proposes VMamba-ADD. Specifically, a residual VMamba branch is incorporated into the U-Net decoder to efficiently capture global context. Meanwhile, an adaptive gating fusion module dynamically integrates global structural priors and local texture features. Furthermore, to suppress cross-step degradation propagation, we adopt the prediction-based self-refinement (PSR) strategy from the baseline ADD framework. Extensive experiments validate that the proposed method effectively suppresses generation artefacts and improves structural coherence. Quantitatively, VMamba-ADD improves the LPIPS metric from 0.3368 to 0.3366 under complex synthetic degradations and achieves a competitive MANIQA score of 0.6213 on the RealLR200 dataset, demonstrating robust perceptual fidelity. VMamba-ADD effectively mitigates the limitations of aggressive distillation. By generating structurally consistent high-resolution images while maintaining highly efficient inference (1–4 steps), it provides a reliable visual foundation for downstream engineering tasks, particularly automated infrastructure defect and crack segmentation.
Zitieren
APA
Liu, T., Liu, Y., Chen, J., Dai, A., Hu, Z., & Zhang, R. (2026). VMamba-ADD: A Dual-Branch Adversarial Diffusion Distillation Network for Efficient Blind Super-Resolution. Applied Sciences, 16(22), 11097. https://doi.org/10.3390/app162211097
Vancouver
Liu T, Liu Y, Chen J, Dai A, Hu Z, Zhang R. VMamba-ADD: A Dual-Branch Adversarial Diffusion Distillation Network for Efficient Blind Super-Resolution. Applied Sciences. 2026;16(22):11097. doi:10.3390/app162211097
BibTeX
@article{Liu2026,
author = {Liu, Tongyan and Liu, Yuxiang and Chen, Jiale and Dai, An’an and Hu, Zishu and Zhang, Ronghua},
title = {VMamba-ADD: A Dual-Branch Adversarial Diffusion Distillation Network for Efficient Blind Super-Resolution},
journal = {Applied Sciences},
year = {2026},
volume = {16},
number = {22},
pages = {11097},
doi = {10.3390/app162211097}
}
EUVIMED