Learning an Implicit Physics Model for Image-based Fluid Simulation

TL;DR

This paper presents a physics-informed neural network that generates realistic 4D fluid animations from a single image by predicting surface point motions guided by physical laws, improving over previous simplistic methods.

Contribution

The paper introduces a novel physics-guided neural network for 4D scene generation from a single image, incorporating Navier-Stokes equations for physically consistent fluid motion prediction.

Findings

Produces physically plausible fluid animations

Outperforms existing methods in realism and accuracy

Effectively captures appearance and motion from a single image

Abstract

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/ .