magicr/phyworld

Dataset

4

stars

32

commits

1

linked in READMEs

Jan 6, 2025

updated

README

Data for PAPER How Far is Video Generation from World Model: A Physical Law Perspective

Project page: https://phyworld.github.io/

Download Data

Data TypeTrain Data (30K/300K/3M)Eval DataDescription
Uniform Motion30K, 300K, 3MEvalEval data includes both in-distribution and out-of-distribution data
Parabola30K, 300K, 3MEval-
Collision30K, 300K, 3MEval-
Combinatorial DataIn-template 6M templates00:59Out-of-templateIn-template-6M includes train data (0:990 videos in each train template) and in-template eval data (990:1000 videos in each train template). Out-template refers to eval data from reserved 10 templates (templates60:69).

Citation

@article{kang2024how,
  title={How Far is Video Generation from World Model? -- A Physical Law Perspective},
  author={Kang, Bingyi and Yue, Yang and Lu, Rui and Lin, Zhijie and Zhao, Yang, and Wang, Kaixin and Gao, Huang and Feng Jiashi},
  journal={arXiv preprint arXiv:2406.16860},
  year={2024}
}

Contributors

Yang130

31 commits

nielsr

1 commits

magicr/phyworld

Dataset

4

stars

32

commits

1

linked in READMEs

Jan 6, 2025

updated

README

Data for PAPER How Far is Video Generation from World Model: A Physical Law Perspective

Project page: https://phyworld.github.io/

Download Data

Data TypeTrain Data (30K/300K/3M)Eval DataDescription
Uniform Motion30K, 300K, 3MEvalEval data includes both in-distribution and out-of-distribution data
Parabola30K, 300K, 3MEval-
Collision30K, 300K, 3MEval-
Combinatorial DataIn-template 6M templates00:59Out-of-templateIn-template-6M includes train data (0:990 videos in each train template) and in-template eval data (990:1000 videos in each train template). Out-template refers to eval data from reserved 10 templates (templates60:69).

Citation

@article{kang2024how,
  title={How Far is Video Generation from World Model? -- A Physical Law Perspective},
  author={Kang, Bingyi and Yue, Yang and Lu, Rui and Lin, Zhijie and Zhao, Yang, and Wang, Kaixin and Gao, Huang and Feng Jiashi},
  journal={arXiv preprint arXiv:2406.16860},
  year={2024}
}

Contributors

Yang130

31 commits

nielsr

1 commits