Lagrangian Neural Style Transfer for Fluids

Byungsoo Kim, Vinicius C. Azevedo, Markus Gross, Barbara Solenthaler
Computer Graphics Lab., ETH Zurich
ACM Transaction on Graphics (Proceedings of SIGGRAPH 2020), arXiv:2005.00803

Our Lagrangian neural style transfer enables novel artistic manipulations, such as time-coherent stylization of smoke, multiple fluids and liquids.

abstract

Artistically controlling the shape, motion and appearance of fluid simulations pose major challenges in visual effects production. In this paper, we present a neural style transfer approach from images to 3D fluids formulated in a Lagrangian viewpoint. Using particles for style transfer has unique benefits compared to grid-based techniques. Attributes are stored on the particles and hence are trivially transported by the particle motion. This intrinsically ensures temporal consistency of the optimized stylized structure and notably improves the resulting quality. Simultaneously, the expensive, recursive alignment of stylization velocity fields of grid approaches is unnecessary, reducing the computation time to less than an hour and rendering neural flow stylization practical in production settings. Moreover, the Lagrangian representation improves artistic control as it allows for multi-fluid stylization and consistent color transfer from images, and the generality of the method enables stylization of smoke and liquids likewise.


video


SIGGRAPH 2020 – Technical Papers Trailer

Two Minute Papers

Fast Forward

download

Paper | Code | Presentation

Bibtex


@article{kim20lnst,
  title={{Lagrangian Neural Style Transfer for Fluids}},
  author={Kim, Byungsoo and C. Azevedo, Vinicius and Gross, Markus and Solenthaler, Barbara},
  journal={ACM Transactions on Graphics},
  volume={39},
  number={4},
  articleno={Article 52},
  numpages={10},
  year={2020},
  issue_date={July 2020},
  doi={10.1145/3386569.3392473},  
  publisher={ACM}  
}
							

Acknowledgement

The authors would like to thank Fraser Rothnie for his artistic contributions. This work was supported by the Swiss National Science Foundation under Grant No. 200021_168997.