BG-HOP: A Bimanual Generative Hand-Object Prior

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Krishna, Sriram, Chittupalli, Sravan, Park, Sungjae
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916790183919616
author Krishna, Sriram
Chittupalli, Sravan
Park, Sungjae
author_facet Krishna, Sriram
Chittupalli, Sravan
Park, Sungjae
contents In this work, we present BG-HOP, a generative prior that seeks to model bimanual hand-object interactions in 3D. We address the challenge of limited bimanual interaction data by extending existing single-hand generative priors, demonstrating preliminary results in capturing the joint distribution of hands and objects. Our experiments showcase the model's capability to generate bimanual interactions and synthesize grasps for given objects. We make code and models publicly available.
format Preprint
id arxiv_https___arxiv_org_abs_2506_09068
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle BG-HOP: A Bimanual Generative Hand-Object Prior
Krishna, Sriram
Chittupalli, Sravan
Park, Sungjae
Computer Vision and Pattern Recognition
Machine Learning
Robotics
In this work, we present BG-HOP, a generative prior that seeks to model bimanual hand-object interactions in 3D. We address the challenge of limited bimanual interaction data by extending existing single-hand generative priors, demonstrating preliminary results in capturing the joint distribution of hands and objects. Our experiments showcase the model's capability to generate bimanual interactions and synthesize grasps for given objects. We make code and models publicly available.
title BG-HOP: A Bimanual Generative Hand-Object Prior
topic Computer Vision and Pattern Recognition
Machine Learning
Robotics
url https://arxiv.org/abs/2506.09068