EUVIMEDEUVIMED entdecken
Crossref

Arbitrary-Scale Video Super-resolution Guided by Dynamic Context

Cong Huang, Jiahao Li, Lei Chu, Dong Liu, Yan Lu

Proceedings of the AAAI Conference on Artificial Intelligence · 24.03.2024 · 38 (3) · 2294-2302

DOI: 10.1609/aaai.v38i3.28003 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 24.03.2024. Verfasst von Cong Huang und 4 weiteren Autor:innen. Die Arbeit wurde bisher 7-mal zitiert (Crossref).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

We propose a Dynamic Context-Guided Upsampling (DCGU) module for video super-resolution (VSR) that leverages temporal context guidance to achieve efficient and effective arbitrary-scale VSR. While most VSR research focuses on backbone design, the importance of the upsampling part is often overlooked. Existing methods rely on pixelshuffle-based upsampling, which has limited capabilities in handling arbitrary upsampling scales. Recent attempts to replace pixelshuffle-based modules with implicit neural function-based and filter-based approaches suffer from slow inference speeds and limited representation capacity, respectively. To overcome these limitations, our DCGU module predicts non-local sampling locations and content-dependent filter weights, enabling efficient and effective arbitrary-scale VSR. Our proposed multi-granularity location search module efficiently identifies non-local sampling locations across the entire low-resolution grid, and the temporal bilateral filter modulation module integrates content information with the filter weight to enhance textual details. Extensive experiments demonstrate the superiority of our method in terms of performance and speed on arbitrary-scale VSR.

Zitieren

APA

Huang, C., Li, J., Chu, L., Liu, D., & Lu, Y. (2024). Arbitrary-Scale Video Super-resolution Guided by Dynamic Context. Proceedings of the AAAI Conference on Artificial Intelligence, 38(3), 2294-2302. https://doi.org/10.1609/aaai.v38i3.28003

Vancouver

Huang C, Li J, Chu L, Liu D, Lu Y. Arbitrary-Scale Video Super-resolution Guided by Dynamic Context. Proceedings of the AAAI Conference on Artificial Intelligence. 2024;38(3):2294-2302. doi:10.1609/aaai.v38i3.28003

BibTeX
@article{Huang2024,
  author = {Huang, Cong and Li, Jiahao and Chu, Lei and Liu, Dong and Lu, Yan},
  title = {Arbitrary-Scale Video Super-resolution Guided by Dynamic Context},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2024},
  volume = {38},
  number = {3},
  pages = {2294--2302},
  doi = {10.1609/aaai.v38i3.28003}
}
Kostenlos starten →