EPS: Efficient Patch Sampling for Video Overfitting in Deep Super-Resolution Model Training
IEEE Transactions on Circuits and Systems for Video Technology · 2026-08 · 36 (8) · 11431-11444
DOI: 10.1109/tcsvt.2026.3684857 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Circuits and Systems for Video Technology, 2026-08. Verfasst von Yiying Wei und 3 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 51 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Austrian Federal Ministry for Digital and Economic Affairs, Österreichische Nationalstiftung für Forschung, Technologie und Entwicklung, Christian Doppler Forschungsgesellschaft.
Abstract (Originalsprache)
Leveraging the overfitting property of deep neural networks (DNNs) is trending in video delivery systems to enhance video quality within bandwidth limits. Existing approaches transmit overfitted super-resolution (SR) model streams for low-resolution (LR) bitstreams, which are used to reconstruct high-resolution (HR) videos at the decoder. Although these approaches show promising results, the huge computational costs of training a large number of video frames limit their practical applications. To overcome this challenge, we propose an efficient patch sampling method named EPS for video SR network overfitting, which identifies the most valuable training patches from video frames. To this end, we first present two low-complexity Discrete Cosine Transform (DCT)-based spatial-temporal features to measure the complexity score of each patch directly. By analyzing the histogram distribution of these features, we then categorize all possible patches into different clusters and select training patches from the cluster with the highest spatial-temporal information. The number of sampled patches is adaptive based on the video content, addressing the trade-off between training complexity and efficiency. Our method reduces the number of training patches by 75.00% to 91.69%, depending on the resolution and number of clusters, while preserving high video quality and greatly improving training efficiency. Our method speeds up patch sampling by up to $82.1\times $ compared to the state-of-the-art patch sampling technique (EMT).
Förderung
- Austrian Federal Ministry for Digital and Economic Affairs
- Österreichische Nationalstiftung für Forschung, Technologie und Entwicklung
- Christian Doppler Forschungsgesellschaft
- Christian Doppler Laboratory ATHENA
Zitieren
APA
Wei, Y., Amirpour, H., Ko, J. H., & Timmerer, C. (2026). EPS: Efficient Patch Sampling for Video Overfitting in Deep Super-Resolution Model Training. IEEE Transactions on Circuits and Systems for Video Technology, 36(8), 11431-11444. https://doi.org/10.1109/tcsvt.2026.3684857
Vancouver
Wei Y, Amirpour H, Ko JH, Timmerer C. EPS: Efficient Patch Sampling for Video Overfitting in Deep Super-Resolution Model Training. IEEE Transactions on Circuits and Systems for Video Technology. 2026;36(8):11431-11444. doi:10.1109/tcsvt.2026.3684857
BibTeX
@article{Wei2026,
author = {Wei, Yiying and Amirpour, Hadi and Ko, Jong Hwan and Timmerer, Christian},
title = {EPS: Efficient Patch Sampling for Video Overfitting in Deep Super-Resolution Model Training},
journal = {IEEE Transactions on Circuits and Systems for Video Technology},
year = {2026},
volume = {36},
number = {8},
pages = {11431--11444},
doi = {10.1109/tcsvt.2026.3684857}
}
EUVIMED