BimArt: A Unified Approach for the Synthesis of 3D Bimanual Interaction with Articulated Objects

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Zhang, Wanyue, Dabral, Rishabh, Golyanik, Vladislav, Choutas, Vasileios, Alvarado, Eduardo, Beeler, Thabo, Habermann, Marc, Theobalt, Christian
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866916661494284288
author Zhang, Wanyue
Dabral, Rishabh
Golyanik, Vladislav
Choutas, Vasileios
Alvarado, Eduardo
Beeler, Thabo
Habermann, Marc
Theobalt, Christian
author_facet Zhang, Wanyue
Dabral, Rishabh
Golyanik, Vladislav
Choutas, Vasileios
Alvarado, Eduardo
Beeler, Thabo
Habermann, Marc
Theobalt, Christian
contents We present BimArt, a novel generative approach for synthesizing 3D bimanual hand interactions with articulated objects. Unlike prior works, we do not rely on a reference grasp, a coarse hand trajectory, or separate modes for grasping and articulating. To achieve this, we first generate distance-based contact maps conditioned on the object trajectory with an articulation-aware feature representation, revealing rich bimanual patterns for manipulation. The learned contact prior is then used to guide our hand motion generator, producing diverse and realistic bimanual motions for object movement and articulation. Our work offers key insights into feature representation and contact prior for articulated objects, demonstrating their effectiveness in taming the complex, high-dimensional space of bimanual hand-object interactions. Through comprehensive quantitative experiments, we demonstrate a clear step towards simplified and high-quality hand-object animations that surpass the state of the art in motion quality and diversity. Project page: https://vcai.mpi-inf.mpg.de/projects/bimart/.
format Preprint
id arxiv_https___arxiv_org_abs_2412_05066
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle BimArt: A Unified Approach for the Synthesis of 3D Bimanual Interaction with Articulated Objects
Zhang, Wanyue
Dabral, Rishabh
Golyanik, Vladislav
Choutas, Vasileios
Alvarado, Eduardo
Beeler, Thabo
Habermann, Marc
Theobalt, Christian
Computer Vision and Pattern Recognition
Graphics
Robotics
We present BimArt, a novel generative approach for synthesizing 3D bimanual hand interactions with articulated objects. Unlike prior works, we do not rely on a reference grasp, a coarse hand trajectory, or separate modes for grasping and articulating. To achieve this, we first generate distance-based contact maps conditioned on the object trajectory with an articulation-aware feature representation, revealing rich bimanual patterns for manipulation. The learned contact prior is then used to guide our hand motion generator, producing diverse and realistic bimanual motions for object movement and articulation. Our work offers key insights into feature representation and contact prior for articulated objects, demonstrating their effectiveness in taming the complex, high-dimensional space of bimanual hand-object interactions. Through comprehensive quantitative experiments, we demonstrate a clear step towards simplified and high-quality hand-object animations that surpass the state of the art in motion quality and diversity. Project page: https://vcai.mpi-inf.mpg.de/projects/bimart/.
title BimArt: A Unified Approach for the Synthesis of 3D Bimanual Interaction with Articulated Objects
topic Computer Vision and Pattern Recognition
Graphics
Robotics
url https://arxiv.org/abs/2412.05066