EUVIMEDEUVIMED entdecken
Crossref

Multi-View Single-Scan Visual State-Space Network for Efficient Image Super-Resolution

Hong Yang, Weihua Liu, Xianqiang Yang

IEEE Transactions on Image Processing · 2026 · 35 · 8021-8033

DOI: 10.1109/tip.2026.3714851 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Image Processing, 2026. Verfasst von Hong Yang und 2 weiteren Autor:innen. Die Arbeit nennt 79 Literaturangaben. Gefördert von: Fundamental Research Funds for the Central Universities.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Single image super-resolution (SISR) seeks to reconstruct high-resolution images from low-resolution inputs under the tight latency and memory budgets of edge devices. Recent visual state space models enable linear-time sequence modeling, but they often approximate two-dimensional dependencies through multiple directional scans, which increases computation and memory. We propose a Multi-View Single-Scan Visual State Space Network (MVSSN) for efficient image super-resolution. MVSSN contains three main components. A shuffled input stacking module (SISM) organizes replicated and shuffled input channels before a lightweight projection, where the learned projection filters help produce less redundant shallow responses. A multi-view single-scan block (MSSB) uses an alternating scan axis and invertible geometric transforms to change the serialization order observed by one selective scan in each block. Across stacked blocks, this provides a lightweight cross-layer approximation to multi-view context modeling. A multi-scale local feature block (MLFB) complements global aggregation with depthwise convolutions of complementary receptive fields and a compact MLP to restore local details. Experiments on standard SISR benchmarks show that MVSSN achieves competitive or better PSNR and SSIM with fewer than one million parameters and low FLOPs. Additional ablations, RealSR evaluations, and downstream detection and segmentation studies further examine its efficiency and practical behavior. We also discuss the limitation under unknown real degradation, where bicubic-trained models may still suffer from domain gaps.

Förderung

  • Fundamental Research Funds for the Central Universities

Zitieren

APA

Yang, H., Liu, W., & Yang, X. (2026). Multi-View Single-Scan Visual State-Space Network for Efficient Image Super-Resolution. IEEE Transactions on Image Processing, 35, 8021-8033. https://doi.org/10.1109/tip.2026.3714851

Vancouver

Yang H, Liu W, Yang X. Multi-View Single-Scan Visual State-Space Network for Efficient Image Super-Resolution. IEEE Transactions on Image Processing. 2026;35:8021-8033. doi:10.1109/tip.2026.3714851

BibTeX
@article{Yang2026,
  author = {Yang, Hong and Liu, Weihua and Yang, Xianqiang},
  title = {Multi-View Single-Scan Visual State-Space Network for Efficient Image Super-Resolution},
  journal = {IEEE Transactions on Image Processing},
  year = {2026},
  volume = {35},
  pages = {8021--8033},
  doi = {10.1109/tip.2026.3714851}
}
Kostenlos starten →