OnRef-VSR: Real-Time Online Reference-Based Video Super-Resolution via Efficient Temporal and Spatial Feature Transfers
IEEE Transactions on Circuits and Systems for Video Technology · 2026-07 · 36 (7) · 10129-10143
DOI: 10.1109/tcsvt.2026.3671415 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Circuits and Systems for Video Technology, 2026-07. Verfasst von Duzhong Feng und 3 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 69 Literaturangaben. Gefördert von: National Key Research and Development Program of China, National Natural Science Foundation of China, Fundamental Research Funds for Central Universities.
Abstract (Originalsprache)
Acquiring high-resolution video is essential in applications such as surveillance, remote sensing, and microscopy. Yet pushing spatial resolution often compromises temporal resolution due to readout and bandwidth limitations. Rather than relying solely on hardware improvements, reference-based video super-resolution (Ref-VSR) provides a promising solution to achieve HR video acquisition with off-the-shelf cameras. However, existing Ref-VSR approaches are predominantly offline, relying on future frames and computationally expensive matching, which fundamentally limits their causal real-time applicability. In addition, the inherent trade-off between reconstruction fidelity and inference speed remains a key obstacle to practical use. To overcome these challenges, we present the first online reference-based video super-resolution framework (OnRef-VSR), which enables causal real-time reconstruction through efficient spatial and temporal feature transfers. The framework incorporates three key modules: Flow-Local Linear Transform-based Feature Enhancement (FLFE) module, Hierarchical Heterogeneous Feature Transfer (HHFT) module, and Detail Refinement with Flow-guided Local nonlinear transform (DRFL) module, which in combination realize effective integration of temporal cues and reference information. Extensive experiments demonstrate the superiority of the proposed approach. Specifically, OnRefVSR achieves a $5.2\times $ faster speed with a 0.29 dB gain over the state-of-the-art real-time method, and its offline variant yields a $3.6\times $ speedup and a 0.84 dB PSNR gain on the standard Vid4 benchmark, confirming both the effectiveness and practicality of OnRef-VSR for real-time high-fidelity video reconstruction.
Förderung
- National Key Research and Development Program of China
- National Natural Science Foundation of China
- Fundamental Research Funds for Central Universities
Zitieren
APA
Feng, D., Qiu, C., Yue, T., & Hu, X. (2026). OnRef-VSR: Real-Time Online Reference-Based Video Super-Resolution via Efficient Temporal and Spatial Feature Transfers. IEEE Transactions on Circuits and Systems for Video Technology, 36(7), 10129-10143. https://doi.org/10.1109/tcsvt.2026.3671415
Vancouver
Feng D, Qiu C, Yue T, Hu X. OnRef-VSR: Real-Time Online Reference-Based Video Super-Resolution via Efficient Temporal and Spatial Feature Transfers. IEEE Transactions on Circuits and Systems for Video Technology. 2026;36(7):10129-10143. doi:10.1109/tcsvt.2026.3671415
BibTeX
@article{Feng2026,
author = {Feng, Duzhong and Qiu, Chenxi and Yue, Tao and Hu, Xuemei},
title = {OnRef-VSR: Real-Time Online Reference-Based Video Super-Resolution via Efficient Temporal and Spatial Feature Transfers},
journal = {IEEE Transactions on Circuits and Systems for Video Technology},
year = {2026},
volume = {36},
number = {7},
pages = {10129--10143},
doi = {10.1109/tcsvt.2026.3671415}
}
EUVIMED