Gespeichert in:
| Hauptverfasser: | , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | https://arxiv.org/abs/2408.10581 |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866908336967909376 |
|---|---|
| author | Yang, Lixin Zhong, Licheng Zhu, Pengxiang Zhan, Xinyu Kong, Junxiao Xu, Jian Lu, Cewu |
| author_facet | Yang, Lixin Zhong, Licheng Zhu, Pengxiang Zhan, Xinyu Kong, Junxiao Xu, Jian Lu, Cewu |
| contents | This work introduces a novel and generalizable multi-view Hand Mesh Reconstruction (HMR) model, named POEM, designed for practical use in real-world hand motion capture scenarios. The advances of the POEM model consist of two main aspects. First, concerning the modeling of the problem, we propose embedding a static basis point within the multi-view stereo space. A point represents a natural form of 3D information and serves as an ideal medium for fusing features across different views, given its varied projections across these views. Consequently, our method harnesses a simple yet effective idea: a complex 3D hand mesh can be represented by a set of 3D basis points that 1) are embedded in the multi-view stereo, 2) carry features from the multi-view images, and 3) encompass the hand in it. The second advance lies in the training strategy. We utilize a combination of five large-scale multi-view datasets and employ randomization in the number, order, and poses of the cameras. By processing such a vast amount of data and a diverse array of camera configurations, our model demonstrates notable generalizability in the real-world applications. As a result, POEM presents a highly practical, plug-and-play solution that enables user-friendly, cost-effective multi-view motion capture for both left and right hands. The model and source codes are available at https://github.com/JubSteven/POEM-v2. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2408_10581 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Multi-view Hand Reconstruction with a Point-Embedded Transformer Yang, Lixin Zhong, Licheng Zhu, Pengxiang Zhan, Xinyu Kong, Junxiao Xu, Jian Lu, Cewu Computer Vision and Pattern Recognition This work introduces a novel and generalizable multi-view Hand Mesh Reconstruction (HMR) model, named POEM, designed for practical use in real-world hand motion capture scenarios. The advances of the POEM model consist of two main aspects. First, concerning the modeling of the problem, we propose embedding a static basis point within the multi-view stereo space. A point represents a natural form of 3D information and serves as an ideal medium for fusing features across different views, given its varied projections across these views. Consequently, our method harnesses a simple yet effective idea: a complex 3D hand mesh can be represented by a set of 3D basis points that 1) are embedded in the multi-view stereo, 2) carry features from the multi-view images, and 3) encompass the hand in it. The second advance lies in the training strategy. We utilize a combination of five large-scale multi-view datasets and employ randomization in the number, order, and poses of the cameras. By processing such a vast amount of data and a diverse array of camera configurations, our model demonstrates notable generalizability in the real-world applications. As a result, POEM presents a highly practical, plug-and-play solution that enables user-friendly, cost-effective multi-view motion capture for both left and right hands. The model and source codes are available at https://github.com/JubSteven/POEM-v2. |
| title | Multi-view Hand Reconstruction with a Point-Embedded Transformer |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2408.10581 |