用物理规则生成单图流体动画，让视频更真实。
Learning an Implicit Physics Model for Image-based Fluid Simulation
- 用神经网络结合流体方程预测每点运动，保证物理合理性。
- 通过3D高斯点云建模外观，实现多视角渲染。
- 适合做影视特效或科学可视化，追求真实感的场景。
人类能从一张静态图像中想象出包含运动与三维结构的四维场景，这源于对相似场景的长期观察和对物理规律的直觉理解。本文旨在让神经网络具备这一能力，聚焦于自然流体图像的4D生成。现有方法通常采用简化的2D运动估计器，导致运动违背物理规律，产生不真实动画。本文提出一种新方法，通过物理信息神经网络预测表面各点运动，损失函数基于基本物理原理（如纳维-斯托克斯方程）。为捕捉外观，从输入图像及其估计深度中预测基于特征的3D高斯分布，并利用预测运动进行动画化，支持任意相机视角渲染。实验表明，该方法在生成物理合理动画方面显著优于现有方法。
原文摘要 · Abstract (English)
Humans possess an exceptional ability to imagine 4D scenes, encompassing both motion and 3D geometry, from a single still image. This ability is rooted in our accumulated observations of similar scenes and an intuitive understanding of physics. In this paper, we aim to replicate this capacity in neural networks, specifically focusing on natural fluid imagery. Existing methods for this task typically employ simplistic 2D motion estimators to animate the image, leading to motion predictions that often defy physical principles, resulting in unrealistic animations. Our approach introduces a novel method for generating 4D scenes with physics-consistent animation from a single image. We propose the use of a physics-informed neural network that predicts motion for each surface point, guided by a loss term derived from fundamental physical principles, including the Navier-Stokes equations. To capture appearance, we predict feature-based 3D Gaussians from the input image and its estimated depth, which are then animated using the predicted motions and rendered from any desired camera perspective. Experimental results highlight the effectiveness of our method in producing physically plausible animations, showcasing significant performance improvements over existing methods. Our project page is https://physfluid.github.io/ .
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。