ArtHOI: Taming Foundation Models for Monocular 4D Reconstruction of Hand-Articulated-Object Interactions
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866918411444944896 |
|---|---|
| author | Wang, Zikai Zhang, Zhilu Wang, Yiqing Li, Hui Zuo, Wangmeng |
| author_facet | Wang, Zikai Zhang, Zhilu Wang, Yiqing Li, Hui Zuo, Wangmeng |
| contents | Existing hand-object interactions (HOI) methods are largely limited to rigid objects, while 4D reconstruction methods of articulated objects generally require pre-scanning the object or even multi-view videos. It remains an unexplored but significant challenge to reconstruct 4D human-articulated-object interactions from a single monocular RGB video. Fortunately, recent advancements in foundation models present a new opportunity to address this highly ill-posed problem. To this end, we introduce ArtHOI, an optimization-based framework that integrates and refines priors from multiple foundation models. Our key contribution is a suite of novel methodologies designed to resolve the inherent inaccuracies and physical unreality of these priors. In particular, we introduce an Adaptive Sampling Refinement (ASR) method to optimize object's metric scale and pose for grounding its normalized mesh in world space. Furthermore, we propose a Multimodal Large Language Model (MLLM) guided hand-object alignment method, utilizing contact reasoning information as constraints of hand-object mesh composition optimization. To facilitate a comprehensive evaluation, we also contribute two new datasets, ArtHOI-RGBD and ArtHOI-Wild. Extensive experiments validate the robustness and effectiveness of our ArtHOI across diverse objects and interactions. Project: https://arthoi-reconstruction.github.io. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_25791 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | ArtHOI: Taming Foundation Models for Monocular 4D Reconstruction of Hand-Articulated-Object Interactions Wang, Zikai Zhang, Zhilu Wang, Yiqing Li, Hui Zuo, Wangmeng Computer Vision and Pattern Recognition Existing hand-object interactions (HOI) methods are largely limited to rigid objects, while 4D reconstruction methods of articulated objects generally require pre-scanning the object or even multi-view videos. It remains an unexplored but significant challenge to reconstruct 4D human-articulated-object interactions from a single monocular RGB video. Fortunately, recent advancements in foundation models present a new opportunity to address this highly ill-posed problem. To this end, we introduce ArtHOI, an optimization-based framework that integrates and refines priors from multiple foundation models. Our key contribution is a suite of novel methodologies designed to resolve the inherent inaccuracies and physical unreality of these priors. In particular, we introduce an Adaptive Sampling Refinement (ASR) method to optimize object's metric scale and pose for grounding its normalized mesh in world space. Furthermore, we propose a Multimodal Large Language Model (MLLM) guided hand-object alignment method, utilizing contact reasoning information as constraints of hand-object mesh composition optimization. To facilitate a comprehensive evaluation, we also contribute two new datasets, ArtHOI-RGBD and ArtHOI-Wild. Extensive experiments validate the robustness and effectiveness of our ArtHOI across diverse objects and interactions. Project: https://arthoi-reconstruction.github.io. |
| title | ArtHOI: Taming Foundation Models for Monocular 4D Reconstruction of Hand-Articulated-Object Interactions |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2603.25791 |