Saved in:
Bibliographic Details
Main Authors: Le, Long, Xie, Jason, Liang, William, Wang, Hung-Ju, Yang, Yue, Ma, Yecheng Jason, Vedder, Kyle, Krishna, Arjun, Jayaraman, Dinesh, Eaton, Eric
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2410.13882
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913869143736320
author Le, Long
Xie, Jason
Liang, William
Wang, Hung-Ju
Yang, Yue
Ma, Yecheng Jason
Vedder, Kyle
Krishna, Arjun
Jayaraman, Dinesh
Eaton, Eric
author_facet Le, Long
Xie, Jason
Liang, William
Wang, Hung-Ju
Yang, Yue
Ma, Yecheng Jason
Vedder, Kyle
Krishna, Arjun
Jayaraman, Dinesh
Eaton, Eric
contents Interactive 3D simulated objects are crucial in AR/VR, animations, and robotics, driving immersive experiences and advanced automation. However, creating these articulated objects requires extensive human effort and expertise, limiting their broader applications. To overcome this challenge, we present Articulate-Anything, a system that automates the articulation of diverse, complex objects from many input modalities, including text, images, and videos. Articulate-Anything leverages vision-language models (VLMs) to generate code that can be compiled into an interactable digital twin for use in standard 3D simulators. Our system exploits existing 3D asset datasets via a mesh retrieval mechanism, along with an actor-critic system that iteratively proposes, evaluates, and refines solutions for articulating the objects, self-correcting errors to achieve a robust outcome. Qualitative evaluations demonstrate Articulate-Anything's capability to articulate complex and even ambiguous object affordances by leveraging rich grounded inputs. In extensive quantitative experiments on the standard PartNet-Mobility dataset, Articulate-Anything substantially outperforms prior work, increasing the success rate from 8.7-11.6% to 75% and setting a new bar for state-of-the-art performance. We further showcase the utility of our system by generating 3D assets from in-the-wild video inputs, which are then used to train robotic policies for fine-grained manipulation tasks in simulation that go beyond basic pick and place. These policies are then transferred to a real robotic system.
format Preprint
id arxiv_https___arxiv_org_abs_2410_13882
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Articulate-Anything: Automatic Modeling of Articulated Objects via a Vision-Language Foundation Model
Le, Long
Xie, Jason
Liang, William
Wang, Hung-Ju
Yang, Yue
Ma, Yecheng Jason
Vedder, Kyle
Krishna, Arjun
Jayaraman, Dinesh
Eaton, Eric
Computer Vision and Pattern Recognition
Interactive 3D simulated objects are crucial in AR/VR, animations, and robotics, driving immersive experiences and advanced automation. However, creating these articulated objects requires extensive human effort and expertise, limiting their broader applications. To overcome this challenge, we present Articulate-Anything, a system that automates the articulation of diverse, complex objects from many input modalities, including text, images, and videos. Articulate-Anything leverages vision-language models (VLMs) to generate code that can be compiled into an interactable digital twin for use in standard 3D simulators. Our system exploits existing 3D asset datasets via a mesh retrieval mechanism, along with an actor-critic system that iteratively proposes, evaluates, and refines solutions for articulating the objects, self-correcting errors to achieve a robust outcome. Qualitative evaluations demonstrate Articulate-Anything's capability to articulate complex and even ambiguous object affordances by leveraging rich grounded inputs. In extensive quantitative experiments on the standard PartNet-Mobility dataset, Articulate-Anything substantially outperforms prior work, increasing the success rate from 8.7-11.6% to 75% and setting a new bar for state-of-the-art performance. We further showcase the utility of our system by generating 3D assets from in-the-wild video inputs, which are then used to train robotic policies for fine-grained manipulation tasks in simulation that go beyond basic pick and place. These policies are then transferred to a real robotic system.
title Articulate-Anything: Automatic Modeling of Articulated Objects via a Vision-Language Foundation Model
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2410.13882