No Labels, No Look-Ahead: Unsupervised Online Video Stabilization with Classical Priors
This work provides a more robust and efficient video stabilization solution for domains like UAV nighttime remote sensing, where existing deep learning methods struggle due to data limitations and resource constraints.
This paper introduces an unsupervised framework for online video stabilization that leverages classical stabilization techniques and a multithreaded buffering mechanism. It outperforms state-of-the-art online stabilizers and achieves performance comparable to offline methods, addressing limitations of deep learning approaches.
We propose a new unsupervised framework for online video stabilization. Unlike methods based on deep learning that require paired stable and unstable datasets, our approach instantiates the classical stabilization pipeline with three stages and incorporates a multithreaded buffering mechanism. This design addresses three longstanding challenges in end-to-end learning: limited data, poor controllability, and inefficiency on hardware with constrained resources. Existing benchmarks focus mainly on handheld videos with a forward view in visible light, which restricts the applicability of stabilization to domains such as UAV nighttime remote sensing. To fill this gap, we introduce a new multimodal UAV aerial video dataset (UAV-Test). Experiments show that our method consistently outperforms state-of-the-art online stabilizers in both quantitative metrics and visual quality, while achieving performance comparable to offline methods.