Learning Continuous Degradation for Real-World Arbitrary-Scale Video Super-Resolution
IEEE Transactions on Circuits and Systems for Video Technology · 2026-05 · 36 (5) · 6037-6050
DOI: 10.1109/tcsvt.2025.3650643 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Circuits and Systems for Video Technology, 2026-05. Verfasst von Wenli Zheng und 6 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 56 Literaturangaben. Gefördert von: Beijing Natural Science Foundation, National Natural Science Foundation of China, National Key Research and Development Program of China.
Abstract (Originalsprache)
Arbitrary-scale video super-resolution (VSR) aims to enhance video resolution at continuous scales and has attracted increasing attention in recent years. However, existing methods typically rely on fixed degradation modes, such as bicubic downsampling, which often fail to handle the complex degradations of real-world videos. Current real-world datasets only cover limited scales (e.g., $\times 2$ , $\times 4$ ) and are insufficient to capture the diverse degradations required for arbitrary-scale VSR. To address this, we present RealArbVSR, the first real-world VSR dataset with both integer and decimal scale factors, providing a wider range of degradation levels. Moreover, to generate continuous degradations beyond the collected scales, we propose the Continuous Degradation Generation Network (CDGN), which synthesizes realistic LR videos with arbitrary degradations. Specifically, we design a Scale-aware Degradation Module (SDM) to adaptively learn scale-specific degradations and an Implicit Filter Module (IFM) that represents spatial-temporal features as a continuous feature domain for arbitrary-scale LR frame generation. Extensive experiments demonstrate that our CDGN trained on RealArbVSR produces high-fidelity LR videos with arbitrary degradations and significantly enhances the performance of VSR models in real-world scenarios.
Förderung
- Beijing Natural Science Foundation
- National Natural Science Foundation of China
- National Key Research and Development Program of China
Zitieren
APA
Zheng, W., Fu, H., Wang, C., Zhang, E., Mao, H., Zhang, H., & Ma, H. (2026). Learning Continuous Degradation for Real-World Arbitrary-Scale Video Super-Resolution. IEEE Transactions on Circuits and Systems for Video Technology, 36(5), 6037-6050. https://doi.org/10.1109/tcsvt.2025.3650643
Vancouver
Zheng W, Fu H, Wang C, Zhang E, Mao H, Zhang H, et al. Learning Continuous Degradation for Real-World Arbitrary-Scale Video Super-Resolution. IEEE Transactions on Circuits and Systems for Video Technology. 2026;36(5):6037-6050. doi:10.1109/tcsvt.2025.3650643
BibTeX
@article{Zheng2026,
author = {Zheng, Wenli and Fu, Huiyuan and Wang, Chuanming and Zhang, Enyuan and Mao, Hengming and Zhang, Heng and Ma, Huadong},
title = {Learning Continuous Degradation for Real-World Arbitrary-Scale Video Super-Resolution},
journal = {IEEE Transactions on Circuits and Systems for Video Technology},
year = {2026},
volume = {36},
number = {5},
pages = {6037--6050},
doi = {10.1109/tcsvt.2025.3650643}
}
EUVIMED