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.
@article{arxiv.2403.14548,
title = {DINO-Tracker: Taming DINO for Self-Supervised Point Tracking in a Single Video},
author = {Narek Tumanyan and Assaf Singer and Shai Bagon and Tali Dekel},
journal= {arXiv preprint arXiv:2403.14548},
year = {2024}
}
Comments
Accepted to ECCV 2024. Project page: https://dino-tracker.github.io/