EUVIMEDEUVIMED entdecken
Crossref

Rotation Equivariant Arbitrary-Scale Image Super-Resolution

Qi Xie, Jiahong Fu, Zongben Xu, Deyu Meng

IEEE Transactions on Pattern Analysis and Machine Intelligence · 2025-12 · 47 (12) · 11382-11399

DOI: 10.1109/tpami.2025.3600126 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Pattern Analysis and Machine Intelligence, 2025-12. Verfasst von Qi Xie und 3 weiteren Autor:innen. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 81 Literaturangaben. Gefördert von: National Key R&D Program of China, China NSFC projects, Tianyuan Fund for Mathematics of the National Natural Science Foundation of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The arbitrary-scale image super-resolution (ASISR), a recent popular topic in computer vision, aims to achieve arbitrary-scale high-resolution recoveries from a low-resolution input image. This task is realized by representing the image as a continuous implicit function through two fundamental modules, a deep-network-based encoder and an implicit neural representation (INR) module. Despite achieving notable progress, a crucial challenge of such a highly ill-posed setting is that many common geometric patterns, such as repetitive textures, edges, or shapes, are seriously warped and deformed in the low-resolution images, naturally leading to unexpected artifacts appearing in their high-resolution recoveries. Embedding rotation equivariance into the ASISR network is thus necessary, as it has been widely demonstrated that this enhancement enables the recovery to faithfully maintain the original orientations and structural integrity of geometric patterns underlying the input image. Motivated by this, we make efforts to construct a rotation equivariant ASISR method in this study. Specifically, we elaborately redesign the basic architectures of INR and encoder modules, incorporating intrinsic rotation equivariance capabilities beyond those of conventional ASISR networks. Through such amelioration, the ASISR network can, for the first time, be implemented with end-to-end rotational equivariance maintained from input to output. We also provide a solid theoretical analysis to evaluate its intrinsic equivariance error, demonstrating its inherent nature of embedding such an equivariance structure. The superiority of the proposed method is substantiated by experiments conducted on both simulated and real datasets. We also validate that the proposed framework can be readily integrated into current ASISR methods in a plug & play manner to further enhance their performance.

Förderung

  • National Key R&D Program of China
  • China NSFC projects
  • Tianyuan Fund for Mathematics of the National Natural Science Foundation of China

Zitieren

APA

Xie, Q., Fu, J., Xu, Z., & Meng, D. (2025). Rotation Equivariant Arbitrary-Scale Image Super-Resolution. IEEE Transactions on Pattern Analysis and Machine Intelligence, 47(12), 11382-11399. https://doi.org/10.1109/tpami.2025.3600126

Vancouver

Xie Q, Fu J, Xu Z, Meng D. Rotation Equivariant Arbitrary-Scale Image Super-Resolution. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2025;47(12):11382-11399. doi:10.1109/tpami.2025.3600126

BibTeX
@article{Xie2025,
  author = {Xie, Qi and Fu, Jiahong and Xu, Zongben and Meng, Deyu},
  title = {Rotation Equivariant Arbitrary-Scale Image Super-Resolution},
  journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
  year = {2025},
  volume = {47},
  number = {12},
  pages = {11382--11399},
  doi = {10.1109/tpami.2025.3600126}
}
Kostenlos starten →