Track-On: Transformer-based Online Point Tracking with Memory
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915129490145280 |
|---|---|
| author | Aydemir, Görkay Cai, Xiongyi Xie, Weidi Güney, Fatma |
| author_facet | Aydemir, Görkay Cai, Xiongyi Xie, Weidi Güney, Fatma |
| contents | In this paper, we consider the problem of long-term point tracking, which requires consistent identification of points across multiple frames in a video, despite changes in appearance, lighting, perspective, and occlusions. We target online tracking on a frame-by-frame basis, making it suitable for real-world, streaming scenarios. Specifically, we introduce Track-On, a simple transformer-based model designed for online long-term point tracking. Unlike prior methods that depend on full temporal modeling, our model processes video frames causally without access to future frames, leveraging two memory modules -- spatial memory and context memory -- to capture temporal information and maintain reliable point tracking over long time horizons. At inference time, it employs patch classification and refinement to identify correspondences and track points with high accuracy. Through extensive experiments, we demonstrate that Track-On sets a new state-of-the-art for online models and delivers superior or competitive results compared to offline approaches on seven datasets, including the TAP-Vid benchmark. Our method offers a robust and scalable solution for real-time tracking in diverse applications. Project page: https://kuis-ai.github.io/track_on |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2501_18487 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Track-On: Transformer-based Online Point Tracking with Memory Aydemir, Görkay Cai, Xiongyi Xie, Weidi Güney, Fatma Computer Vision and Pattern Recognition In this paper, we consider the problem of long-term point tracking, which requires consistent identification of points across multiple frames in a video, despite changes in appearance, lighting, perspective, and occlusions. We target online tracking on a frame-by-frame basis, making it suitable for real-world, streaming scenarios. Specifically, we introduce Track-On, a simple transformer-based model designed for online long-term point tracking. Unlike prior methods that depend on full temporal modeling, our model processes video frames causally without access to future frames, leveraging two memory modules -- spatial memory and context memory -- to capture temporal information and maintain reliable point tracking over long time horizons. At inference time, it employs patch classification and refinement to identify correspondences and track points with high accuracy. Through extensive experiments, we demonstrate that Track-On sets a new state-of-the-art for online models and delivers superior or competitive results compared to offline approaches on seven datasets, including the TAP-Vid benchmark. Our method offers a robust and scalable solution for real-time tracking in diverse applications. Project page: https://kuis-ai.github.io/track_on |
| title | Track-On: Transformer-based Online Point Tracking with Memory |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2501.18487 |