OpenHOI: Open-World Hand-Object Interaction Synthesis with Multimodal Large Language Model

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhang, Zhenhao, Shi, Ye, Yang, Lingxiao, Ni, Suting, Ye, Qi, Wang, Jingya
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914211453468672
author Zhang, Zhenhao
Shi, Ye
Yang, Lingxiao
Ni, Suting
Ye, Qi
Wang, Jingya
author_facet Zhang, Zhenhao
Shi, Ye
Yang, Lingxiao
Ni, Suting
Ye, Qi
Wang, Jingya
contents Understanding and synthesizing realistic 3D hand-object interactions (HOI) is critical for applications ranging from immersive AR/VR to dexterous robotics. Existing methods struggle with generalization, performing well on closed-set objects and predefined tasks but failing to handle unseen objects or open-vocabulary instructions. We introduce OpenHOI, the first framework for open-world HOI synthesis, capable of generating long-horizon manipulation sequences for novel objects guided by free-form language commands. Our approach integrates a 3D Multimodal Large Language Model (MLLM) fine-tuned for joint affordance grounding and semantic task decomposition, enabling precise localization of interaction regions (e.g., handles, buttons) and breakdown of complex instructions (e.g., "Find a water bottle and take a sip") into executable sub-tasks. To synthesize physically plausible interactions, we propose an affordance-driven diffusion model paired with a training-free physics refinement stage that minimizes penetration and optimizes affordance alignment. Evaluations across diverse scenarios demonstrate OpenHOI's superiority over state-of-the-art methods in generalizing to novel object categories, multi-stage tasks, and complex language instructions. Our project page at \href{https://openhoi.github.io}
format Preprint
id arxiv_https___arxiv_org_abs_2505_18947
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle OpenHOI: Open-World Hand-Object Interaction Synthesis with Multimodal Large Language Model
Zhang, Zhenhao
Shi, Ye
Yang, Lingxiao
Ni, Suting
Ye, Qi
Wang, Jingya
Computer Vision and Pattern Recognition
Understanding and synthesizing realistic 3D hand-object interactions (HOI) is critical for applications ranging from immersive AR/VR to dexterous robotics. Existing methods struggle with generalization, performing well on closed-set objects and predefined tasks but failing to handle unseen objects or open-vocabulary instructions. We introduce OpenHOI, the first framework for open-world HOI synthesis, capable of generating long-horizon manipulation sequences for novel objects guided by free-form language commands. Our approach integrates a 3D Multimodal Large Language Model (MLLM) fine-tuned for joint affordance grounding and semantic task decomposition, enabling precise localization of interaction regions (e.g., handles, buttons) and breakdown of complex instructions (e.g., "Find a water bottle and take a sip") into executable sub-tasks. To synthesize physically plausible interactions, we propose an affordance-driven diffusion model paired with a training-free physics refinement stage that minimizes penetration and optimizes affordance alignment. Evaluations across diverse scenarios demonstrate OpenHOI's superiority over state-of-the-art methods in generalizing to novel object categories, multi-stage tasks, and complex language instructions. Our project page at \href{https://openhoi.github.io}
title OpenHOI: Open-World Hand-Object Interaction Synthesis with Multimodal Large Language Model
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2505.18947