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

arXiv:2404.12383v1 Announce Type: new
Abstract: 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. To learn a 3D spatial diffusion model that can capture this joint distribution, we represent the human hand via a skeletal distance field to obtain a representation aligned with the (latent) signed distance field for the object. We show that this hand-object prior can then serve as …

3d object abstract arxiv cs.cv denoising diffusion diffusion model distribution generative human interactions learn modeling object prior spatial synthesis type