EasyHOI: Unleashing the Power of Large Models for Reconstructing Hand-Object Interactions in the Wild
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866908720530718720 |
|---|---|
| author | Liu, Yumeng Long, Xiaoxiao Yang, Zemin Liu, Yuan Habermann, Marc Theobalt, Christian Ma, Yuexin Wang, Wenping |
| author_facet | Liu, Yumeng Long, Xiaoxiao Yang, Zemin Liu, Yuan Habermann, Marc Theobalt, Christian Ma, Yuexin Wang, Wenping |
| contents | Our work aims to reconstruct hand-object interactions from a single-view image, which is a fundamental but ill-posed task. Unlike methods that reconstruct from videos, multi-view images, or predefined 3D templates, single-view reconstruction faces significant challenges due to inherent ambiguities and occlusions. These challenges are further amplified by the diverse nature of hand poses and the vast variety of object shapes and sizes. Our key insight is that current foundational models for segmentation, inpainting, and 3D reconstruction robustly generalize to in-the-wild images, which could provide strong visual and geometric priors for reconstructing hand-object interactions. Specifically, given a single image, we first design a novel pipeline to estimate the underlying hand pose and object shape using off-the-shelf large models. Furthermore, with the initial reconstruction, we employ a prior-guided optimization scheme, which optimizes hand pose to comply with 3D physical constraints and the 2D input image content. We perform experiments across several datasets and show that our method consistently outperforms baselines and faithfully reconstructs a diverse set of hand-object interactions. Here is the link of our project page: https://lym29.github.io/EasyHOI-page/ |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2411_14280 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | EasyHOI: Unleashing the Power of Large Models for Reconstructing Hand-Object Interactions in the Wild Liu, Yumeng Long, Xiaoxiao Yang, Zemin Liu, Yuan Habermann, Marc Theobalt, Christian Ma, Yuexin Wang, Wenping Computer Vision and Pattern Recognition Our work aims to reconstruct hand-object interactions from a single-view image, which is a fundamental but ill-posed task. Unlike methods that reconstruct from videos, multi-view images, or predefined 3D templates, single-view reconstruction faces significant challenges due to inherent ambiguities and occlusions. These challenges are further amplified by the diverse nature of hand poses and the vast variety of object shapes and sizes. Our key insight is that current foundational models for segmentation, inpainting, and 3D reconstruction robustly generalize to in-the-wild images, which could provide strong visual and geometric priors for reconstructing hand-object interactions. Specifically, given a single image, we first design a novel pipeline to estimate the underlying hand pose and object shape using off-the-shelf large models. Furthermore, with the initial reconstruction, we employ a prior-guided optimization scheme, which optimizes hand pose to comply with 3D physical constraints and the 2D input image content. We perform experiments across several datasets and show that our method consistently outperforms baselines and faithfully reconstructs a diverse set of hand-object interactions. Here is the link of our project page: https://lym29.github.io/EasyHOI-page/ |
| title | EasyHOI: Unleashing the Power of Large Models for Reconstructing Hand-Object Interactions in the Wild |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2411.14280 |