Minimum Latency Deep Online Video Stabilization and Its Extensions
IEEE Transactions on Pattern Analysis and Machine Intelligence · 2025-02 · 47 (2) · 1238-1249
DOI: 10.1109/tpami.2024.3493175 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Pattern Analysis and Machine Intelligence, 2025-02. Verfasst von Shuaicheng Liu und 4 weiteren Autor:innen. Die Arbeit wurde bisher 13-mal zitiert (Crossref) und nennt 52 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Natural Science Foundation of Sichuan Province.
Abstract (Originalsprache)
We present a novel deep camera path optimization framework for minimum latency online video stabilization. Typically, a stabilization pipeline consists of three steps: motion estimation, path smoothing, and novel view synthesis. Most previous methods concentrate on motion estimation while path optimization receives less attention, particularly in the crucial online setting where future frames are inaccessible. In this work, we adopt off-the-shelf high-quality deep motion models for motion estimation and focus only on the path optimization. Specifically, our camera path smoothing network takes a short 2D camera path in a sliding window as input and outputs the stabilizing warp field of the last frame, which warps the coming frame to its stabilized position. We explore three motion densities: a global single camera path, local mesh-based bundled paths, and dense flow paths. A hybrid loss and an efficient motion smoothing attention (EMSA) module are proposed for spatially and temporally consistent path smoothing. Moreover, we build a motion dataset that contains stable and unstable motion pairs for training. Extensive experiments demonstrate that our method surpasses state-of-the-art online stabilization methods and rivals the performance of offline methods, offering compelling advancements in the field of video stabilization.
Förderung
- National Natural Science Foundation of China
- Natural Science Foundation of Sichuan Province
Zitieren
APA
Liu, S., Zhang, Z., Liu, Z., Tan, P., & Zeng, B. (2025). Minimum Latency Deep Online Video Stabilization and Its Extensions. IEEE Transactions on Pattern Analysis and Machine Intelligence, 47(2), 1238-1249. https://doi.org/10.1109/tpami.2024.3493175
Vancouver
Liu S, Zhang Z, Liu Z, Tan P, Zeng B. Minimum Latency Deep Online Video Stabilization and Its Extensions. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2025;47(2):1238-1249. doi:10.1109/tpami.2024.3493175
BibTeX
@article{Liu2025,
author = {Liu, Shuaicheng and Zhang, Zhuofan and Liu, Zhen and Tan, Ping and Zeng, Bing},
title = {Minimum Latency Deep Online Video Stabilization and Its Extensions},
journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
year = {2025},
volume = {47},
number = {2},
pages = {1238--1249},
doi = {10.1109/tpami.2024.3493175}
}
EUVIMED