Neural Smoke Stylization with Color Transfer

Fabienne Christen, Byungsoo Kim, Vinicius C. Azevedo, Barbara Solenthaler
ETH Zurich
Eurographics & Eurovis 2020 Short Paper, arXiv:1912.08757

abstract

Artistically controlling fluid simulations requires a large amount of manual work by an artist. The recently presented transport-based neural style transfer approach simplifies workflows as it transfers the style of arbitrary input images onto 3D smoke simulations. However, the method only modifies the shape of the fluid but omits color information. In this work, we therefore extend the previous approach to obtain a complete pipeline for transferring shape and color information onto 2D and 3D smoke simulations with neural networks. Our results demonstrate that our method successfully transfers colored style features consistently in space and time to smoke data for different input textures.


video



Presentation


download

Paper

Bibtex


@article{christen19color,
	author = {Christen, Fabienne and Kim, Byungsoo and C. Azevedo, Vinicius and Solenthaler, Barbara},
	title = {{Neural Smoke Stylization with Color Transfer}},
	year = {2020},
	month = {may},
	booktitle = {EGEV 2020 - Short Papers},
	publisher = {The Eurographics Association},
}
							

Acknowledgement

The authors would like to thank Ondrej Jamriska for sharing his dataset. This work was supported by the Swiss National Science Foundation (grant No. 200021_168997).