Kubric Dataset for CoTracker 3

Overview

This dataset was specifically created for training CoTracker 3, a state-of-the-art point tracking model. The dataset was generated using the Kubric engine.

Dataset Specifications

• Size: ~6,000 sequences
• Resolution: 512×512 pixels
• Sequence Length: 120 frames per sequence
• Camera Movement: Carefully rendered with subtle camera motion to simulate realistic scenarios
• Format: Generated using Kubric engine

Usage

The dataset can be parsed using the official CoTracker implementation. For detailed parsing instructions, refer to:

• CoTracker Dataset Parser
• Kubric Engine Repository

Citation

If you use this dataset in your research, please cite the following papers:

@inproceedings{karaev24cotracker3,
  title     = {CoTracker3: Simpler and Better Point Tracking by Pseudo-Labelling Real Videos},
  author    = {Nikita Karaev and Iurii Makarov and Jianyuan Wang and Natalia Neverova and Andrea Vedaldi and Christian Rupprecht},  
  booktitle = {Proc. {arXiv:2410.11831}},
  year      = {2024}
}

@article{greff2021kubric,
    title = {Kubric: a scalable dataset generator}, 
    author = {Klaus Greff and Francois Belletti and Lucas Beyer and Carl Doersch and
              Yilun Du and Daniel Duckworth and David J Fleet and Dan Gnanapragasam and
              Florian Golemo and Charles Herrmann and Thomas Kipf and Abhijit Kundu and
              Dmitry Lagun and Issam Laradji and Hsueh-Ti (Derek) Liu and Henning Meyer and
              Yishu Miao and Derek Nowrouzezahrai and Cengiz Oztireli and Etienne Pot and
              Noha Radwan and Daniel Rebain and Sara Sabour and Mehdi S. M. Sajjadi and Matan Sela and
              Vincent Sitzmann and Austin Stone and Deqing Sun and Suhani Vora and Ziyu Wang and
              Tianhao Wu and Kwang Moo Yi and Fangcheng Zhong and Andrea Tagliasacchi},
    booktitle = {Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
    year = {2022},
}