无需标注、无需前瞻：结合经典先验的无监督在线视频稳定
No Labels, No Look-Ahead: Unsupervised Online Video Stabilization with Classical Priors
将经典三阶段稳定流程（轨迹估计-平滑-补偿）嵌入无监督在线框架，并用多线程缓冲解决端到端学习的可控性与效率问题；对做视频时序处理、在线流式视觉任务的人，这是一个可复用的「经典先验+无监督」范式，同时 UAV-Test 多模态航拍数据集可支撑夜间遥感场景的稳定化评测。
原文依据 our method models the classical three-stage stabilization pipeline and integrates a multithreaded buffering mechanism
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论我们提出了一种新的无监督在线视频稳定框架。与需要成对稳定/不稳定数据集的深度学习稳定器不同，我们的方法对经典三阶段稳定流程进行建模，并集成多线程缓冲机制，有效解决了端到端学习的三个关键挑战：数据有限、可控性差以及在资源受限硬件上效率低下。现有基准主要关注手持、前视、可见光视频，限制了稳定技术在无人机夜间遥感等领域的应用。为填补这一空白，我们引入了一个新的多模态无人机航拍视频数据集（UAV-Test）。实验表明，我们的方法在定量指标和视觉质量上均持续优于最优的在线稳定器，同时达到与离线方法相当的性能。
英文原文摘要 905 字符
We propose a novel unsupervised framework for online video stabilization. Unlike deep learning-based stabilizers that require paired stable/unstable datasets, our method models the classical three-stage stabilization pipeline and integrates a multithreaded buffering mechanism, effectively addressing three key challenges of end-to-end learning: limited data, poor controllability, and inefficiency on resource-constrained hardware. Existing benchmarks mainly focus on handheld, forward-view, visible-light videos, restricting the application of stabilization in 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 approach consistently outperforms state-of-the-art online stabilizers in both quantitative metrics and visual quality, while achieving performance comparable to that of offline methods.