PGC: Physics-Based Gaussian Cloth from a Single Pose
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866915214261223424 |
|---|---|
| author | Guo, Michelle Chiang, Matt Jen-Yuan Santesteban, Igor Sarafianos, Nikolaos Chen, Hsiao-yu Halimi, Oshri Božič, Aljaž Saito, Shunsuke Wu, Jiajun Liu, C. Karen Stuyck, Tuur Larionov, Egor |
| author_facet | Guo, Michelle Chiang, Matt Jen-Yuan Santesteban, Igor Sarafianos, Nikolaos Chen, Hsiao-yu Halimi, Oshri Božič, Aljaž Saito, Shunsuke Wu, Jiajun Liu, C. Karen Stuyck, Tuur Larionov, Egor |
| contents | We introduce a novel approach to reconstruct simulation-ready garments with intricate appearance. Despite recent advancements, existing methods often struggle to balance the need for accurate garment reconstruction with the ability to generalize to new poses and body shapes or require large amounts of data to achieve this. In contrast, our method only requires a multi-view capture of a single static frame. We represent garments as hybrid mesh-embedded 3D Gaussian splats, where the Gaussians capture near-field shading and high-frequency details, while the mesh encodes far-field albedo and optimized reflectance parameters. We achieve novel pose generalization by exploiting the mesh from our hybrid approach, enabling physics-based simulation and surface rendering techniques, while also capturing fine details with Gaussians that accurately reconstruct garment details. Our optimized garments can be used for simulating garments on novel poses, and garment relighting. Project page: https://phys-gaussian-cloth.github.io . |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_20779 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | PGC: Physics-Based Gaussian Cloth from a Single Pose Guo, Michelle Chiang, Matt Jen-Yuan Santesteban, Igor Sarafianos, Nikolaos Chen, Hsiao-yu Halimi, Oshri Božič, Aljaž Saito, Shunsuke Wu, Jiajun Liu, C. Karen Stuyck, Tuur Larionov, Egor Graphics I.3.6; I.3.7 We introduce a novel approach to reconstruct simulation-ready garments with intricate appearance. Despite recent advancements, existing methods often struggle to balance the need for accurate garment reconstruction with the ability to generalize to new poses and body shapes or require large amounts of data to achieve this. In contrast, our method only requires a multi-view capture of a single static frame. We represent garments as hybrid mesh-embedded 3D Gaussian splats, where the Gaussians capture near-field shading and high-frequency details, while the mesh encodes far-field albedo and optimized reflectance parameters. We achieve novel pose generalization by exploiting the mesh from our hybrid approach, enabling physics-based simulation and surface rendering techniques, while also capturing fine details with Gaussians that accurately reconstruct garment details. Our optimized garments can be used for simulating garments on novel poses, and garment relighting. Project page: https://phys-gaussian-cloth.github.io . |
| title | PGC: Physics-Based Gaussian Cloth from a Single Pose |
| topic | Graphics I.3.6; I.3.7 |
| url | https://arxiv.org/abs/2503.20779 |