CoWTracker：以变形替代相关性的跟踪方法
CoWTracker: Tracking by Warping instead of Correlation
用基于当前跟踪估计的特征变形（warping）替代代价体做跨帧匹配，把复杂度从空间分辨率的平方降到线性，并用 Transformer 对所有轨迹做联合时空推理；做视频对应、光流或长程跟踪的工作可以直接复用这一迭代变形框架，并把它当作统一稠密点跟踪与光流估计的骨干设计。
原文依据 iteratively refines track estimates by warping features from the target frame to the query frame based on the current track estimate
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论当前最优的点跟踪器通常依赖代价体来匹配跨帧特征，但该做法在空间分辨率上具有二次复杂度，限制了可扩展性与效率。本文提出 CoWTracker，一种新颖的稠密点跟踪器，它摒弃代价体而改用变形。受光流领域近期进展的启发，我们的方法基于当前轨迹估计将目标帧的特征变形到查询帧，从而迭代地精化轨迹估计。结合一个对所有轨迹执行联合时空推理的 Transformer，我们的设计无需计算特征相关性即可建立长程对应关系。该模型结构简单，在标准稠密点跟踪基准（包括 TAP-Vid-DAVIS、TAP-Vid-Kinetics 和 Robo-TAP）上取得了最优性能。值得注意的是，该模型在光流任务上同样表现出色，在 Sintel、KITTI 和 Spring 基准上有时甚至优于专门方法。这些结果表明，基于变形的架构能够统一稠密点跟踪与光流估计。
英文原文摘要 1107 字符
State-of-the-art point trackers typically rely on cost volumes to match features across frames, but this approach incurs quadratic complexity in spatial resolution, limiting scalability and efficiency. In this paper, we propose CoWTracker, a novel dense point tracker that eschews cost volumes in favor of warping. Inspired by recent advances in optical flow, our approach iteratively refines track estimates by warping features from the target frame to the query frame based on the current track estimate. Combined with a transformer that performs joint spatiotemporal reasoning across all tracks, our design establishes long-range correspondences without computing feature correlations. Our model is simple and achieves state-of-the-art performance on standard dense point tracking benchmarks, including TAP-Vid-DAVIS, TAP-Vid-Kinetics, and Robo-TAP. Remarkably, the model also excels at optical flow, sometimes outperforming specialized methods on the Sintel, KITTI, and Spring benchmarks. These results suggest that warping-based architectures can unify dense point tracking and optical flow estimation.