Instructions to use google/tapnet with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use google/tapnet with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("google/tapnet", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Add missing citations: RoboTAP, TAPVid-3D, TRAJAN
Browse files
README.md
CHANGED
|
@@ -145,6 +145,20 @@ If you use these models, please cite the relevant papers:
|
|
| 145 |
```
|
| 146 |
</details>
|
| 147 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 148 |
<details>
|
| 149 |
<summary>BootsTAP (ACCV 2024)</summary>
|
| 150 |
|
|
@@ -158,6 +172,19 @@ If you use these models, please cite the relevant papers:
|
|
| 158 |
```
|
| 159 |
</details>
|
| 160 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 161 |
<details>
|
| 162 |
<summary>TAPNext (ICCV 2025)</summary>
|
| 163 |
|
|
@@ -172,6 +199,19 @@ If you use these models, please cite the relevant papers:
|
|
| 172 |
```
|
| 173 |
</details>
|
| 174 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 175 |
<details>
|
| 176 |
<summary>TAPNext++ (CVPR 2026 Findings)</summary>
|
| 177 |
|
|
|
|
| 145 |
```
|
| 146 |
</details>
|
| 147 |
|
| 148 |
+
<details>
|
| 149 |
+
<summary>RoboTAP (ICRA 2024)</summary>
|
| 150 |
+
|
| 151 |
+
```bibtex
|
| 152 |
+
@article{vecerik2023robotap,
|
| 153 |
+
title={{RoboTAP}: Tracking arbitrary points for few-shot visual imitation},
|
| 154 |
+
author={Vecerik, Mel and Doersch, Carl and Yang, Yi and Davchev, Todor and Aytar, Yusuf and Zhou, Guangyao and Hadsell, Raia and Agapito, Lourdes and Scholz, Jon},
|
| 155 |
+
journal={International Conference on Robotics and Automation},
|
| 156 |
+
pages={5397--5403},
|
| 157 |
+
year={2024}
|
| 158 |
+
}
|
| 159 |
+
```
|
| 160 |
+
</details>
|
| 161 |
+
|
| 162 |
<details>
|
| 163 |
<summary>BootsTAP (ACCV 2024)</summary>
|
| 164 |
|
|
|
|
| 172 |
```
|
| 173 |
</details>
|
| 174 |
|
| 175 |
+
<details>
|
| 176 |
+
<summary>TAPVid-3D (NeurIPS 2024)</summary>
|
| 177 |
+
|
| 178 |
+
```bibtex
|
| 179 |
+
@article{koppula2024tapvid,
|
| 180 |
+
title={{TAPVid}-{3D}: A Benchmark for Tracking Any Point in {3D}},
|
| 181 |
+
author={Koppula, Skanda and Rocco, Ignacio and Yang, Yi and Heyward, Joe and Carreira, Jo{\~a}o and Zisserman, Andrew and Brostow, Gabriel and Doersch, Carl},
|
| 182 |
+
journal={Advances in Neural Information Processing Systems},
|
| 183 |
+
year={2024}
|
| 184 |
+
}
|
| 185 |
+
```
|
| 186 |
+
</details>
|
| 187 |
+
|
| 188 |
<details>
|
| 189 |
<summary>TAPNext (ICCV 2025)</summary>
|
| 190 |
|
|
|
|
| 199 |
```
|
| 200 |
</details>
|
| 201 |
|
| 202 |
+
<details>
|
| 203 |
+
<summary>TRAJAN (2025)</summary>
|
| 204 |
+
|
| 205 |
+
```bibtex
|
| 206 |
+
@article{allen2025trajan,
|
| 207 |
+
title={Direct Motion Models for Assessing Generated Videos},
|
| 208 |
+
author={Allen, Kelsey and Doersch, Carl and Zhou, Guangyao and Suhail, Mohammed and Driess, Danny and Rocco, Ignacio and Rubanova, Yulia and Kipf, Thomas and Sajjadi, Mehdi S. M. and Murphy, Kevin and Carreira, Joao and van Steenkiste, Sjoerd},
|
| 209 |
+
journal={arXiv preprint},
|
| 210 |
+
year={2025}
|
| 211 |
+
}
|
| 212 |
+
```
|
| 213 |
+
</details>
|
| 214 |
+
|
| 215 |
<details>
|
| 216 |
<summary>TAPNext++ (CVPR 2026 Findings)</summary>
|
| 217 |
|