Neural Kinematic Bases for Fluids
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866916978052038656 |
|---|---|
| author | Liu, Yibo Fang, Zhixin Darkner, Sune Aigerman, Noam Erleben, Kenny Kry, Paul Schneider, Teseo |
| author_facet | Liu, Yibo Fang, Zhixin Darkner, Sune Aigerman, Noam Erleben, Kenny Kry, Paul Schneider, Teseo |
| contents | We propose mesh-free fluid simulations that exploit a kinematic neural basis for velocity fields represented by an MLP. We design a set of losses that ensures that these neural bases approximate fundamental physical properties such as orthogonality, divergence-free, boundary alignment, and smoothness. Our neural bases can then be used to fit an input sketch of a flow, which will inherit the same fundamental properties from the bases. We then can animate such flow in real-time using standard time integrators. Our neural bases can accommodate different domains, moving boundaries, and naturally extend to three dimensions. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_15657 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Neural Kinematic Bases for Fluids Liu, Yibo Fang, Zhixin Darkner, Sune Aigerman, Noam Erleben, Kenny Kry, Paul Schneider, Teseo Graphics Machine Learning Fluid Dynamics We propose mesh-free fluid simulations that exploit a kinematic neural basis for velocity fields represented by an MLP. We design a set of losses that ensures that these neural bases approximate fundamental physical properties such as orthogonality, divergence-free, boundary alignment, and smoothness. Our neural bases can then be used to fit an input sketch of a flow, which will inherit the same fundamental properties from the bases. We then can animate such flow in real-time using standard time integrators. Our neural bases can accommodate different domains, moving boundaries, and naturally extend to three dimensions. |
| title | Neural Kinematic Bases for Fluids |
| topic | Graphics Machine Learning Fluid Dynamics |
| url | https://arxiv.org/abs/2504.15657 |