Volumetric Temporal Texture Synthesis for Smoke Stylization using Neural Cellular Automata
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866929715245219840 |
|---|---|
| author | Wang, Dongqing Pajouheshgar, Ehsan Xu, Yitao Zhang, Tong Süsstrunk, Sabine |
| author_facet | Wang, Dongqing Pajouheshgar, Ehsan Xu, Yitao Zhang, Tong Süsstrunk, Sabine |
| contents | Artistic stylization of 3D volumetric smoke data is still a challenge in computer graphics due to the difficulty of ensuring spatiotemporal consistency given a reference style image, and that within reasonable time and computational resources. In this work, we introduce Volumetric Neural Cellular Automata (VNCA), a novel model for efficient volumetric style transfer that synthesizes, in real-time, multi-view consistent stylizing features on the target smoke with temporally coherent transitions between stylized simulation frames. VNCA synthesizes a 3D texture volume with color and density stylization and dynamically aligns this volume with the intricate motion patterns of the smoke simulation under the Eulerian framework. Our approach replaces the explicit fluid advection modeling and the inter-frame smoothing terms with the self-emerging motion of the underlying cellular automaton, thus reducing the training time by over an order of magnitude. Beyond smoke simulations, we demonstrate the versatility of our approach by showcasing its applicability to mesh stylization. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_09631 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Volumetric Temporal Texture Synthesis for Smoke Stylization using Neural Cellular Automata Wang, Dongqing Pajouheshgar, Ehsan Xu, Yitao Zhang, Tong Süsstrunk, Sabine Image and Video Processing Graphics Artistic stylization of 3D volumetric smoke data is still a challenge in computer graphics due to the difficulty of ensuring spatiotemporal consistency given a reference style image, and that within reasonable time and computational resources. In this work, we introduce Volumetric Neural Cellular Automata (VNCA), a novel model for efficient volumetric style transfer that synthesizes, in real-time, multi-view consistent stylizing features on the target smoke with temporally coherent transitions between stylized simulation frames. VNCA synthesizes a 3D texture volume with color and density stylization and dynamically aligns this volume with the intricate motion patterns of the smoke simulation under the Eulerian framework. Our approach replaces the explicit fluid advection modeling and the inter-frame smoothing terms with the self-emerging motion of the underlying cellular automaton, thus reducing the training time by over an order of magnitude. Beyond smoke simulations, we demonstrate the versatility of our approach by showcasing its applicability to mesh stylization. |
| title | Volumetric Temporal Texture Synthesis for Smoke Stylization using Neural Cellular Automata |
| topic | Image and Video Processing Graphics |
| url | https://arxiv.org/abs/2502.09631 |