让追踪点始终待在物体内部，提升长期追踪稳定性
Leveraging Object Priors for Point Tracking
- 训练时引入物体先验正则化，强制点保持在物体边界内
- 在三个基准上达到当前最优性能，显著减少误漂移
- 无需测试时计算掩码，适合实时应用如AR与机器人
点追踪是计算机视觉中的基础问题，在增强现实和机器人领域有广泛应用。长期追踪中常见失败情况是预测点脱离所属物体，落在背景或其他物体上。我们发现这是由于学习追踪时未能正确捕捉物体属性（objectness）。为解决这一问题，提出一种新型物体先验正则化方法，通过训练时强制点保持在物体实例边界内，实现对物体属性的建模，避免测试时需计算物体掩码。同时，利用上下文注意力机制增强特征表示，更有效地捕捉物体属性。实验表明，该方法在三个点追踪基准上均达到当前最优性能，并通过消融实验证明各组件有效性。代码已开源。
原文摘要 · Abstract (English)
Point tracking is a fundamental problem in computer vision with numerous applications in AR and robotics. A common failure mode in long-term point tracking occurs when the predicted point leaves the object it belongs to and lands on the background or another object. We identify this as the failure to correctly capture objectness properties in learning to track. To address this limitation of prior work, we propose a novel objectness regularization approach that guides points to be aware of object priors by forcing them to stay inside the the boundaries of object instances. By capturing objectness cues at training time, we avoid the need to compute object masks during testing. In addition, we leverage contextual attention to enhance the feature representation for capturing objectness at the feature level more effectively. As a result, our approach achieves state-of-the-art performance on three point tracking benchmarks, and we further validate the effectiveness of our components via ablation studies. The source code is available at: https://github.com/RehgLab/tracking_objectness
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。