Saved in:
Bibliographic Details
Main Authors: Wang, Shibo, He, Haonan, Parelli, Maria, Gebhardt, Christoph, Fan, Zicong, Song, Jie
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2508.05506
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911096055529472
author Wang, Shibo
He, Haonan
Parelli, Maria
Gebhardt, Christoph
Fan, Zicong
Song, Jie
author_facet Wang, Shibo
He, Haonan
Parelli, Maria
Gebhardt, Christoph
Fan, Zicong
Song, Jie
contents Most RGB-based hand-object reconstruction methods rely on object templates, while template-free methods typically assume full object visibility. This assumption often breaks in real-world settings, where fixed camera viewpoints and static grips leave parts of the object unobserved, resulting in implausible reconstructions. To overcome this, we present MagicHOI, a method for reconstructing hands and objects from short monocular interaction videos, even under limited viewpoint variation. Our key insight is that, despite the scarcity of paired 3D hand-object data, large-scale novel view synthesis diffusion models offer rich object supervision. This supervision serves as a prior to regularize unseen object regions during hand interactions. Leveraging this insight, we integrate a novel view synthesis model into our hand-object reconstruction framework. We further align hand to object by incorporating visible contact constraints. Our results demonstrate that MagicHOI significantly outperforms existing state-of-the-art hand-object reconstruction methods. We also show that novel view synthesis diffusion priors effectively regularize unseen object regions, enhancing 3D hand-object reconstruction.
format Preprint
id arxiv_https___arxiv_org_abs_2508_05506
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle MagicHOI: Leveraging 3D Priors for Accurate Hand-object Reconstruction from Short Monocular Video Clips
Wang, Shibo
He, Haonan
Parelli, Maria
Gebhardt, Christoph
Fan, Zicong
Song, Jie
Computer Vision and Pattern Recognition
Most RGB-based hand-object reconstruction methods rely on object templates, while template-free methods typically assume full object visibility. This assumption often breaks in real-world settings, where fixed camera viewpoints and static grips leave parts of the object unobserved, resulting in implausible reconstructions. To overcome this, we present MagicHOI, a method for reconstructing hands and objects from short monocular interaction videos, even under limited viewpoint variation. Our key insight is that, despite the scarcity of paired 3D hand-object data, large-scale novel view synthesis diffusion models offer rich object supervision. This supervision serves as a prior to regularize unseen object regions during hand interactions. Leveraging this insight, we integrate a novel view synthesis model into our hand-object reconstruction framework. We further align hand to object by incorporating visible contact constraints. Our results demonstrate that MagicHOI significantly outperforms existing state-of-the-art hand-object reconstruction methods. We also show that novel view synthesis diffusion priors effectively regularize unseen object regions, enhancing 3D hand-object reconstruction.
title MagicHOI: Leveraging 3D Priors for Accurate Hand-object Reconstruction from Short Monocular Video Clips
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2508.05506