DINO-Tracker：驯服DINO以实现单视频自监督点跟踪
DINO-Tracker: Taming DINO for Self-Supervised Point Tracking in a Single Video
AI总结：
本研究提出DINO-Tracker框架，结合单视频测试时训练与预训练DINO-ViT的语义特征，通过自监督损失和正则化端到端训练，在基准测试中达到SOTA，长期遮挡场景下优于监督跟踪器。
摘要：
我们提出了DINO-Tracker——一种用于视频中长期密集跟踪的新框架。我们方法的核心是将单视频测试时训练，与预训练DINO-ViT模型学习到的强大局部语义特征相结合。具体而言，我们的框架同时利用DINO的特征来适配测试视频的运动观测，同时训练一个直接利用优化后特征的跟踪器。整个框架通过自监督损失组合，以及能让我们保留并受益于DINO语义先验的正则化，进行端到端训练。大量评估表明，我们的方法在已知基准上取得了当前最优结果。DINO-Tracker显著优于自监督方法，性能与当前最优的监督跟踪器相当，且在长期遮挡的挑战性跟踪场景下表现更优。
英文摘要：
We present DINO-Tracker -- a new framework for long-term dense tracking in video. The pillar of our approach is combining test-time training on a single video, with the powerful localized semantic features learned by a pre-trained DINO-ViT model. Specifically, our framework simultaneously adopts DINO's features to fit to the motion observations of the test video, while training a tracker that directly leverages the refined features. The entire framework is trained end-to-end using a combination of self-supervised losses, and regularization that allows us to retain and benefit from DINO's semantic prior. Extensive evaluation demonstrates that our method achieves state-of-the-art results on known benchmarks. DINO-tracker significantly outperforms self-supervised methods and is competitive with state-of-the-art supervised trackers, while outperforming them in challenging cases of tracking under long-term occlusions.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
