EUVIMEDEUVIMED entdecken
Crossref

Reference-Based Super-Resolution With Geometry-Aware Transfer

Ke Zhang, Lei Huang, Jie Nie, Yadong Huo, Jin Du, Zhiqiang Wei

IEEE Transactions on Circuits and Systems for Video Technology · 2026-08 · 36 (8) · 12025-12038

DOI: 10.1109/tcsvt.2026.3682968 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Circuits and Systems for Video Technology, 2026-08. Verfasst von Ke Zhang und 5 weiteren Autor:innen. Die Arbeit nennt 62 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Natural Science Foundation of Shandong Province, National Key Research and Development Program of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Reference-based super-resolution (RefSR) leverages an additional high-resolution (HR) image as supplementary information to super-resolve a low-resolution (LR) image, generally yielding superior results over single image super-resolution (SISR). Nevertheless, existing RefSR methods still struggle with accurate reference texture transfer, especially under geometric transformations between the input LR and reference images. This issue mainly arises from the improper design of current coupled transfer frameworks, which perform alignment and aggregation jointly within a single step. The resulting degradation gap and disproportion gap impair alignment and aggregation, respectively, while their coupling further aggravates the transfer difficulty through mutual interference. This motivates us to propose a novel RefSR framework with geometry-aware transfer, termed GeoRef, which explicitly decouples texture transfer process to borrow realistic texture across geometric transformations. For the degradation gap, we propose a progressive alignment network that leverages more detailed guidance from SISR and HR images to incrementally refine textures in a coarse-to-fine manner, thereby producing faithful details while suppressing incongruous artifacts. For the disproportion gap, we design a selective aggregation network that adaptively transfers multiple correlated textures according to the object scale ratio between the two images, thereby complementing more relevant information. Additionally, extensive experiments on both reference-based and single image datasets demonstrate that our GeoRef framework achieves competitive performance with state-of-the-art methods in both quantitative and qualitative comparisons. The source codes are available at https://github.com/huanglab-research/GeoRef

Förderung

  • National Natural Science Foundation of China
  • Natural Science Foundation of Shandong Province
  • National Key Research and Development Program of China

Zitieren

APA

Zhang, K., Huang, L., Nie, J., Huo, Y., Du, J., & Wei, Z. (2026). Reference-Based Super-Resolution With Geometry-Aware Transfer. IEEE Transactions on Circuits and Systems for Video Technology, 36(8), 12025-12038. https://doi.org/10.1109/tcsvt.2026.3682968

Vancouver

Zhang K, Huang L, Nie J, Huo Y, Du J, Wei Z. Reference-Based Super-Resolution With Geometry-Aware Transfer. IEEE Transactions on Circuits and Systems for Video Technology. 2026;36(8):12025-12038. doi:10.1109/tcsvt.2026.3682968

BibTeX
@article{Zhang2026,
  author = {Zhang, Ke and Huang, Lei and Nie, Jie and Huo, Yadong and Du, Jin and Wei, Zhiqiang},
  title = {Reference-Based Super-Resolution With Geometry-Aware Transfer},
  journal = {IEEE Transactions on Circuits and Systems for Video Technology},
  year = {2026},
  volume = {36},
  number = {8},
  pages = {12025--12038},
  doi = {10.1109/tcsvt.2026.3682968}
}
Kostenlos starten →