BG-HOP: A Bimanual Generative Hand-Object Prior
This work addresses a domain-specific problem in robotics or computer vision for generating realistic bimanual interactions, but it is incremental as it builds on existing single-hand priors.
The paper tackles the problem of modeling bimanual hand-object interactions in 3D by developing BG-HOP, a generative prior that extends single-hand priors to address limited data, demonstrating preliminary results in generating interactions and grasps.
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.