# Transport-Based Neural Style Transfer for Smoke Simulations

arXiv: https://arxiv.org/abs/1905.07442 · HTML: https://mlsanity.com/paper/1905.07442/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 May 2019.

## Built on by (most cited first, 10 of 10)

- [A survey of synthetic data augmentation methods in computer vision](https://mlsanity.com/paper/2403.10075/) (2024)
- [Global Transport for Fluid Reconstruction with Learned Self-Supervision](https://mlsanity.com/paper/2104.06031/) (2021)
- [Fluid Simulation on Neural Flow Maps](https://mlsanity.com/paper/2312.14635/) (2023)
- [Advances in 3D Neural Stylization: A Survey](https://mlsanity.com/paper/2311.18328/) (2023)
- [Learning to Estimate Single-View Volumetric Flow Motions without 3D Supervision](https://mlsanity.com/paper/2302.14470/) (2023)
- [3DStyleGLIP: Part-Tailored Text-Guided 3D Neural Stylization](https://mlsanity.com/paper/2404.02634/) (2024)
- [Stylos: Multi-View 3D Stylization with Single-Forward Gaussian Splatting](https://mlsanity.com/paper/2509.26455/) (2025)
- [Volumetric Cloud Field Reconstruction](https://mlsanity.com/paper/2311.17657/) (2023)
- [StyleCity: Large-Scale 3D Urban Scenes Stylization](https://mlsanity.com/paper/2404.10681/) (2024)
- [UStyle: Waterbody Style Transfer of Underwater Scenes by Depth-Guided Feature Synthesis](https://mlsanity.com/paper/2503.11893/) (2025)

## Abstract (arXiv)

Artistically controlling fluids has always been a challenging task. Optimization techniques rely on approximating simulation states towards target velocity or density field configurations, which are often handcrafted by artists to indirectly control smoke dynamics. Patch synthesis techniques transfer image textures or simulation features to a target flow field. However, these are either limited to adding structural patterns or augmenting coarse flows with turbulent structures, and hence cannot capture the full spectrum of different styles and semantically complex structures. In this paper, we propose the first Transport-based Neural Style Transfer (TNST) algorithm for volumetric smoke data. Our method is able to transfer features from natural images to smoke simulations, enabling general content-aware manipulations ranging from simple patterns to intricate motifs. The proposed algorithm is physically inspired, since it computes the density transport from a source input smoke to a desired target configuration. Our transport-based approach allows direct control over the divergence of the stylization velocity field by optimizing incompressible and irrotational potentials that transport smoke towards stylization. Temporal consistency is ensured by transporting and aligning subsequent stylized velocities, and 3D reconstructions are computed by seamlessly merging stylizations from different camera viewpoints.