Neural Garment Dynamics via Manifold-Aware Transformers
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866917715143294976 |
|---|---|
| author | Li, Peizhuo Wang, Tuanfeng Y. Kesdogan, Timur Levent Ceylan, Duygu Sorkine-Hornung, Olga |
| author_facet | Li, Peizhuo Wang, Tuanfeng Y. Kesdogan, Timur Levent Ceylan, Duygu Sorkine-Hornung, Olga |
| contents | Data driven and learning based solutions for modeling dynamic garments have significantly advanced, especially in the context of digital humans. However, existing approaches often focus on modeling garments with respect to a fixed parametric human body model and are limited to garment geometries that were seen during training. In this work, we take a different approach and model the dynamics of a garment by exploiting its local interactions with the underlying human body. Specifically, as the body moves, we detect local garment-body collisions, which drive the deformation of the garment. At the core of our approach is a mesh-agnostic garment representation and a manifold-aware transformer network design, which together enable our method to generalize to unseen garment and body geometries. We evaluate our approach on a wide variety of garment types and motion sequences and provide competitive qualitative and quantitative results with respect to the state of the art. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_06101 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Neural Garment Dynamics via Manifold-Aware Transformers Li, Peizhuo Wang, Tuanfeng Y. Kesdogan, Timur Levent Ceylan, Duygu Sorkine-Hornung, Olga Graphics Computer Vision and Pattern Recognition Data driven and learning based solutions for modeling dynamic garments have significantly advanced, especially in the context of digital humans. However, existing approaches often focus on modeling garments with respect to a fixed parametric human body model and are limited to garment geometries that were seen during training. In this work, we take a different approach and model the dynamics of a garment by exploiting its local interactions with the underlying human body. Specifically, as the body moves, we detect local garment-body collisions, which drive the deformation of the garment. At the core of our approach is a mesh-agnostic garment representation and a manifold-aware transformer network design, which together enable our method to generalize to unseen garment and body geometries. We evaluate our approach on a wide variety of garment types and motion sequences and provide competitive qualitative and quantitative results with respect to the state of the art. |
| title | Neural Garment Dynamics via Manifold-Aware Transformers |
| topic | Graphics Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2407.06101 |