从单段野外视频重建动态3D烟雾，支持交互式编辑。
WildSmoke: Ready-to-Use Dynamic 3D Smoke Assets from a Single Video in the Wild
- 从真实环境视频中提取烟雾并重建3D动态模型。
- 在野外视频上实现平均PSNR提升2.22分，优于现有方法。
- 可直接用于烟雾设计与编辑，适合影视特效与游戏开发。
我们提出一种从单个野外视频中提取并重建动态3D烟雾资产的流程，并进一步集成交互式模拟以支持烟雾设计与编辑。近年来3D视觉的发展显著提升了流体动力学的重建与渲染能力，实现了逼真且时间一致的视图合成。然而，当前的流体重建仍依赖于精心控制的洁净实验室环境，而真实世界中拍摄的野外视频尚未被充分探索。我们识别出三个关键挑战：烟雾提取与背景去除、烟雾粒子与相机位姿初始化、多视角视频推断。所提方法不仅在野外视频上实现了平均PSNR提升2.22分，显著优于以往重建与生成方法，还通过模拟重建的烟雾资产，实现了多样且真实的流体动态编辑。相关模型、数据与4D烟雾资产已公开于[https://autumnyq.github.io/WildSmoke](https://autumnyq.github.io/WildSmoke)。
原文摘要 · Abstract (English)
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).
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。