SmokeSVD：基于扩散模型渐进式新视角合成与细化的单视图烟雾重建
SmokeSVD: Smoke Reconstruction from A Single View via Progressive Novel View Synthesis and Refinement with Diffusion Models
利用扩散模型生成物理约束下的侧视图，缓解单视图重建的不适定性，并通过渐进式多阶段新视角合成与可微平流优化重建动态烟雾的密度与速度场，为稀疏视角动态流体重建提供了可复用的生成式先验与优化框架。
原文依据 we first propose a physically guided side-view synthesizer based on diffusion models, which explicitly incorporates velocity field constraints
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论从稀疏视角重建动态流体是一个长期存在且具有挑战性的问题，因为视角覆盖不足导致严重缺乏三维信息。尽管一些开创性方法尝试使用可微渲染或新视角合成来解决这一问题，但它们往往受限于不适定条件下耗时的优化过程。我们提出了 SmokeSVD，一个高效且有效的框架，通过将扩散模型的生成能力与物理引导的一致性优化相结合，从单个视频中渐进式地重建动态烟雾。具体而言，我们首先提出了一种基于扩散模型的物理引导侧视图合成器，它显式地结合速度场约束，逐帧生成时空一致的侧视图图像，显著缓解了单视图重建的不适定性。随后，我们通过一个渐进式多阶段过程迭代地细化新视角图像并重建三维密度场，该过程从递增的视角渲染并增强图像，生成高质量的多视角序列。最后，我们利用纳维-斯托克斯方程通过可微平流估计细粒度的密度场和速度场。我们的方法支持重模拟和下游应用，同时与最优方法相比实现了更优的重建质量和计算效率。
英文原文摘要 1469 字符
Reconstructing dynamic fluids from sparse views is a long-standing and challenging problem, due to the severe lack of 3D information from insufficient view coverage. While several pioneering approaches have attempted to address this issue using differentiable rendering or novel view synthesis, they are often limited by time-consuming optimization under ill-posed conditions. We propose SmokeSVD, an efficient and effective framework to progressively reconstruct dynamic smoke from a single video by integrating the generative capabilities of diffusion models with physically guided consistency optimization. Specifically, we first propose a physically guided side-view synthesizer based on diffusion models, which explicitly incorporates velocity field constraints to generate spatio-temporally consistent side-view images frame by frame, significantly alleviating the ill-posedness of single-view reconstruction. Subsequently, we iteratively refine novel-view images and reconstruct 3D density fields through a progressive multi-stage process that renders and enhances images from increasing viewing angles, generating high-quality multi-view sequences. Finally, we estimate fine-grained density and velocity fields via differentiable advection by leveraging the Navier-Stokes equations. Our approach supports re-simulation and downstream applications while achieving superior reconstruction quality and computational efficiency compared to state-of-the-art methods.