Lagrangian Neural Style Transfer for Fluids
arXiv:2005.00803 · doi:10.1145/3386569.3392473
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.
ACM Transaction on Graphics (SIGGRAPH 2020), additional materials: http://www.byungsoo.me/project/lnst/index.html
References in corpus (10)
- Perspective Transformer Nets: Learning Single-View 3D Object Reconstruction without 3D Supervision
- Accelerating Eulerian Fluid Simulation With Convolutional Networks
- Differentiable Surface Splatting for Point-based Geometry Processing
- tempoGAN: A Temporally Coherent, Volumetric GAN for Super-resolution Fluid Flow
- Data-Driven Synthesis of Smoke Flows with CNN-based Feature Descriptors
- Transport-Based Neural Style Transfer for Smoke Simulations
- Smoothed Particle Hydrodynamics Techniques for the Physics Based Simulation of Fluids and Solids
- Learning to Control PDEs with Differentiable Physics
- Interpolations of Smoke and Liquid Simulations
- Neural Smoke Stylization with Color Transfer