Neural Smoke Stylization with Color Transfer
Fabienne Christen, Byungsoo Kim, Vinicius C. Azevedo, Barbara, Solenthaler

TL;DR
This paper extends neural style transfer for smoke simulations to include color transfer, enabling artists to more easily apply artistic styles with both shape and color to 3D and 2D smoke data.
Contribution
It introduces a complete pipeline for transferring both shape and color styles onto smoke simulations using neural networks, improving upon previous shape-only methods.
Findings
Successfully transfers colored style features onto smoke data
Maintains style consistency in space and time
Works for both 2D and 3D smoke simulations
Abstract
Artistically controlling fluid simulations requires a large amount of manual work by an artist. The recently presented transportbased 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.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
