Skinned Motion Retargeting with Dense Geometric Interaction Perception
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909457467834368 |
|---|---|
| author | Ye, Zijie Liu, Jia-Wei Jia, Jia Sun, Shikun Shou, Mike Zheng |
| author_facet | Ye, Zijie Liu, Jia-Wei Jia, Jia Sun, Shikun Shou, Mike Zheng |
| contents | Capturing and maintaining geometric interactions among different body parts is crucial for successful motion retargeting in skinned characters. Existing approaches often overlook body geometries or add a geometry correction stage after skeletal motion retargeting. This results in conflicts between skeleton interaction and geometry correction, leading to issues such as jittery, interpenetration, and contact mismatches. To address these challenges, we introduce a new retargeting framework, MeshRet, which directly models the dense geometric interactions in motion retargeting. Initially, we establish dense mesh correspondences between characters using semantically consistent sensors (SCS), effective across diverse mesh topologies. Subsequently, we develop a novel spatio-temporal representation called the dense mesh interaction (DMI) field. This field, a collection of interacting SCS feature vectors, skillfully captures both contact and non-contact interactions between body geometries. By aligning the DMI field during retargeting, MeshRet not only preserves motion semantics but also prevents self-interpenetration and ensures contact preservation. Extensive experiments on the public Mixamo dataset and our newly-collected ScanRet dataset demonstrate that MeshRet achieves state-of-the-art performance. Code available at https://github.com/abcyzj/MeshRet. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_20986 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Skinned Motion Retargeting with Dense Geometric Interaction Perception Ye, Zijie Liu, Jia-Wei Jia, Jia Sun, Shikun Shou, Mike Zheng Computer Vision and Pattern Recognition Graphics Capturing and maintaining geometric interactions among different body parts is crucial for successful motion retargeting in skinned characters. Existing approaches often overlook body geometries or add a geometry correction stage after skeletal motion retargeting. This results in conflicts between skeleton interaction and geometry correction, leading to issues such as jittery, interpenetration, and contact mismatches. To address these challenges, we introduce a new retargeting framework, MeshRet, which directly models the dense geometric interactions in motion retargeting. Initially, we establish dense mesh correspondences between characters using semantically consistent sensors (SCS), effective across diverse mesh topologies. Subsequently, we develop a novel spatio-temporal representation called the dense mesh interaction (DMI) field. This field, a collection of interacting SCS feature vectors, skillfully captures both contact and non-contact interactions between body geometries. By aligning the DMI field during retargeting, MeshRet not only preserves motion semantics but also prevents self-interpenetration and ensures contact preservation. Extensive experiments on the public Mixamo dataset and our newly-collected ScanRet dataset demonstrate that MeshRet achieves state-of-the-art performance. Code available at https://github.com/abcyzj/MeshRet. |
| title | Skinned Motion Retargeting with Dense Geometric Interaction Perception |
| topic | Computer Vision and Pattern Recognition Graphics |
| url | https://arxiv.org/abs/2410.20986 |