irmvlab/diff-ip2d

Diff-IP2D

This is the official implementation for our paper:

Diff-IP2D: Diffusion-Based Hand-Object Interaction Prediction on Egocentric Videos.

Junyi Ma, Jingyi Xu, Xieyuanli Chen, Hesheng Wang*

Diff-IP2D is the first work to jointly forecast future hand trajectories and object affordances by the devised denoising diffusion probabilistic model with only 2D egocentric videos as input. It provides a foundation generative paradigm in the field of HOI prediction.

@article{ma2024diffip2d,
  title={Diff-IP2D: Diffusion-Based Hand-Object Interaction Prediction on Egocentric Videos},
  author={Ma, Junyi and Xu, Jingyi and Chen, Xieyuanli and Wang, Hesheng},
  journal={arXiv preprint arXiv:2405.04370},
  year={2024}
}

We will release the code and relevant data upon the acceptance of our paper.