# WildSmoke: Ready-to-Use Dynamic 3D Smoke Assets from a Single Video in the Wild

arXiv: https://arxiv.org/abs/2509.11114 · HTML: https://mlsanity.com/paper/2509.11114/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 28 of its 47 references that are in the map.
- First posted on arXiv 14 Sep 2025.

## Builds on (most cited first, 28 of 28)

- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [3D Gaussian Splatting for Real-Time Radiance Field Rendering](https://mlsanity.com/paper/2308.04079/) (2023)
- [DreamFusion: Text-to-3D using 2D Diffusion](https://mlsanity.com/paper/2209.14988/) (2022)
- [DUSt3R: Geometric 3D Vision Made Easy](https://mlsanity.com/paper/2312.14132/) (2023)
- [Zero-1-to-3: Zero-shot One Image to 3D Object](https://mlsanity.com/paper/2303.11328/) (2023)
- [Structured 3D Latents for Scalable and Versatile 3D Generation](https://mlsanity.com/paper/2412.01506/) (2024)
- [Deep Multi-scale Convolutional Neural Network for Dynamic Scene Deblurring](https://mlsanity.com/paper/1612.02177/) (2016)
- [ViewCrafter: Taming Video Diffusion Models for High-fidelity Novel View Synthesis](https://mlsanity.com/paper/2409.02048/) (2024)
- [DeblurGAN: Blind Motion Deblurring Using Conditional Adversarial Networks](https://mlsanity.com/paper/1711.07064/) (2017)
- [Hunyuan3D 2.0: Scaling Diffusion Models for High Resolution Textured 3D Assets Generation](https://mlsanity.com/paper/2501.12202/) (2025)
- [Images Speak in Images: A Generalist Painter for In-Context Visual Learning](https://mlsanity.com/paper/2212.02499/) (2022)
- [Vision Transformers for Single Image Dehazing](https://mlsanity.com/paper/2204.03883/) (2022)
- [DiffTaichi: Differentiable Programming for Physical Simulation](https://mlsanity.com/paper/1910.00935/) (2019)
- [Stable Virtual Camera: Generative View Synthesis with Diffusion Models](https://mlsanity.com/paper/2503.14489/) (2025)
- [Deep Learning Methods for Reynolds-Averaged Navier-Stokes Simulations of Airfoil Flows](https://mlsanity.com/paper/1810.08217/) (2018)
- [SV4D: Dynamic 3D Content Generation with Multi-Frame and Multi-View Consistency](https://mlsanity.com/paper/2407.17470/) (2024)
- [Physics Informed Neural Fields for Smoke Reconstruction with Sparse Data](https://mlsanity.com/paper/2206.06577/) (2022)
- [SV4D 2.0: Enhancing Spatio-Temporal Consistency in Multi-View Video Diffusion for High-Quality 4D Generation](https://mlsanity.com/paper/2503.16396/) (2025)
- [Aerial Imagery Pile burn detection using Deep Learning: the FLAME dataset](https://mlsanity.com/paper/2012.14036/) (2020)
- [NeuroFluid: Fluid Dynamics Grounding with Particle-Driven Neural Radiance Fields](https://mlsanity.com/paper/2203.01762/) (2022)
- [FluidNexus: 3D Fluid Reconstruction and Prediction from a Single Video](https://mlsanity.com/paper/2503.04720/) (2025)
- [Inferring Hybrid Neural Fluid Fields from Videos](https://mlsanity.com/paper/2312.06561/) (2023)
- [Learning Vortex Dynamics for Fluid Inference and Prediction](https://mlsanity.com/paper/2301.11494/) (2023)
- [Fluid Simulation on Neural Flow Maps](https://mlsanity.com/paper/2312.14635/) (2023)
- [Lagrangian Neural Style Transfer for Fluids](https://mlsanity.com/paper/2005.00803/) (2020)
- [Dynamic Upsampling of Smoke through Dictionary-based Learning](https://mlsanity.com/paper/1910.09166/) (2019)
- [EngineBench: Flow Reconstruction in the Transparent Combustion Chamber III Optical Engine](https://mlsanity.com/paper/2406.03325/) (2024)

## Built on by (most cited first, 1 of 1)

- [FluidGaussian: Propagating Simulation-Based Uncertainty Toward Functionally-Intelligent 3D Reconstruction](https://mlsanity.com/paper/2603.21356/) (2026)

## Abstract (arXiv)

We propose a pipeline to extract and reconstruct dynamic 3D smoke assets from a single in-the-wild video, and further integrate interactive simulation for smoke design and editing. Recent developments in 3D vision have significantly improved reconstructing and rendering fluid dynamics, supporting realistic and temporally consistent view synthesis. However, current fluid reconstructions rely heavily on carefully controlled clean lab environments, whereas real-world videos captured in the wild are largely underexplored. We pinpoint three key challenges of reconstructing smoke in real-world videos and design targeted techniques, including smoke extraction with background removal, initialization of smoke particles and camera poses, and inferring multi-view videos. Our method not only outperforms previous reconstruction and generation methods with high-quality smoke reconstructions (+2.22 average PSNR on wild videos), but also enables diverse and realistic editing of fluid dynamics by simulating our smoke assets. We provide our models, data, and 4D smoke assets at [https://autumnyq.github.io/WildSmoke](https://autumnyq.github.io/WildSmoke).