EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

MambaOSR: Leveraging Spatial-Frequency Mamba for Distortion-Guided Omnidirectional Image Super-Resolution

Weilei Wen iD, Qianqian Zhao iD, Xiuli Shao

Entropy · 20.04.2025 · 27 (4) · 446

DOI: 10.3390/e27040446 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Entropy, online erschienen am 20.04.2025. Verfasst von Weilei Wen und 2 weiteren Autor:innen. Beteiligte Einrichtung: VCIP, College of Computer Science, Nankai University, Tianjin 300350, China. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 57 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: the National Natural Science Foundation of China under Grants, the National Natural Science Foundation of China.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Omnidirectional image super-resolution (ODISR) is critical for VR/AR applications, as high-quality 360° visual content significantly enhances immersive experiences. However, existing ODISR methods suffer from limited receptive fields and high computational complexity, which restricts their ability to model long-range dependencies and extract global structural features. Consequently, these limitations hinder the effective reconstruction of high-frequency details. To address these issues, we propose a novel Mamba-based ODISR network, termed MambaOSR, which consists of three key modules working collaboratively for accurate reconstruction. Specifically, we first introduce a spatial-frequency visual state space model (SF-VSSM) to capture global contextual information via dual-domain representation learning, thereby enhancing the preservation of high-frequency details. Subsequently, we design a distortion-guided module (DGM) that leverages distortion map priors to adaptively model geometric distortions, effectively suppressing artifacts resulting from equirectangular projections. Finally, we develop a multi-scale feature fusion module (MFFM) that integrates complementary features across multiple scales, further improving reconstruction quality. Extensive experiments conducted on the SUN360 dataset demonstrate that our proposed MambaOSR achieves a 0.16 dB improvement in WS-PSNR and increases the mutual information by 1.99% compared with state-of-the-art methods, significantly enhancing both visual quality and the information richness of omnidirectional images.

Schlagwörter

Stichwörter der Autor:innen

Mambamutual informationomnidirectional image super-resolutionspatial frequency

Autor:innen und Institutionen

  • VCIP, College of Computer Science, Nankai University, Tianjin 300350, China.

ORCID-Profile: Weilei Wen, Qianqian Zhao

Förderung

  • the National Natural Science Foundation of China under Grants
  • the National Natural Science Foundation of China

Zitieren

APA

Wen, W., Zhao, Q., & Shao, X. (2025). MambaOSR: Leveraging Spatial-Frequency Mamba for Distortion-Guided Omnidirectional Image Super-Resolution. Entropy, 27(4), 446. https://doi.org/10.3390/e27040446

Vancouver

Wen W, Zhao Q, Shao X. MambaOSR: Leveraging Spatial-Frequency Mamba for Distortion-Guided Omnidirectional Image Super-Resolution. Entropy. 2025;27(4):446. doi:10.3390/e27040446

BibTeX
@article{Wen2025,
  author = {Wen, Weilei and Zhao, Qianqian and Shao, Xiuli},
  title = {MambaOSR: Leveraging Spatial-Frequency Mamba for Distortion-Guided Omnidirectional Image Super-Resolution},
  journal = {Entropy},
  year = {2025},
  volume = {27},
  number = {4},
  pages = {446},
  doi = {10.3390/e27040446}
}
Kostenlos starten →