ShapeShifter: 3D Variations Using Multiscale and Sparse Point-Voxel Diffusion
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866915201255735296 |
|---|---|
| author | Maruani, Nissim Yifan, Wang Fisher, Matthew Alliez, Pierre Desbrun, Mathieu |
| author_facet | Maruani, Nissim Yifan, Wang Fisher, Matthew Alliez, Pierre Desbrun, Mathieu |
| contents | This paper proposes ShapeShifter, a new 3D generative model that learns to synthesize shape variations based on a single reference model. While generative methods for 3D objects have recently attracted much attention, current techniques often lack geometric details and/or require long training times and large resources. Our approach remedies these issues by combining sparse voxel grids and point, normal, and color sampling within a multiscale neural architecture that can be trained efficiently and in parallel. We show that our resulting variations better capture the fine details of their original input and can handle more general types of surfaces than previous SDF-based methods. Moreover, we offer interactive generation of 3D shape variants, allowing more human control in the design loop if needed. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_02187 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | ShapeShifter: 3D Variations Using Multiscale and Sparse Point-Voxel Diffusion Maruani, Nissim Yifan, Wang Fisher, Matthew Alliez, Pierre Desbrun, Mathieu Computer Vision and Pattern Recognition Artificial Intelligence This paper proposes ShapeShifter, a new 3D generative model that learns to synthesize shape variations based on a single reference model. While generative methods for 3D objects have recently attracted much attention, current techniques often lack geometric details and/or require long training times and large resources. Our approach remedies these issues by combining sparse voxel grids and point, normal, and color sampling within a multiscale neural architecture that can be trained efficiently and in parallel. We show that our resulting variations better capture the fine details of their original input and can handle more general types of surfaces than previous SDF-based methods. Moreover, we offer interactive generation of 3D shape variants, allowing more human control in the design loop if needed. |
| title | ShapeShifter: 3D Variations Using Multiscale and Sparse Point-Voxel Diffusion |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2502.02187 |