WildSmoke: Ready-to-Use Dynamic 3D Smoke Assets from a Single Video in the Wild
This enables realistic smoke design and editing from uncontrolled videos, addressing a gap in fluid dynamics reconstruction for applications like visual effects.
The authors tackled the problem of reconstructing dynamic 3D smoke from a single real-world video, achieving high-quality reconstructions with a +2.22 average PSNR improvement over previous methods.
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).