G-HOP: Generative Hand-Object Prior for Interaction Reconstruction and Grasp Synthesis

We propose G-HOP, a denoising diffusion based generative prior for hand-object interactions that allows modeling both the 3D object and a human hand, conditioned on the object category.

Data and Resources

Cite this as

Yufei Ye, Abhinav Gupta, Shubham Tulsiani, Kris Kitani (2024). Dataset: G-HOP: Generative Hand-Object Prior for Interaction Reconstruction and Grasp Synthesis. https://doi.org/10.57702/kdtove2h

DOI retrieved: December 3, 2024

Additional Info

Field Value
Created December 3, 2024
Last update December 3, 2024
Defined In https://doi.org/10.48550/arXiv.2404.12383
Author Yufei Ye
More Authors
Abhinav Gupta
Shubham Tulsiani
Kris Kitani
Homepage https://judyye.github.io/ghop-www