Particle-Based Fluid Surface Rendering with Neural Networks

Surface reconstruction for particle-based fluid simulation is a computational challenge on par with the simula-tion itself. In real-time applications, splatting-style rendering approaches based on forward rendering of particleimpostors are prevalent, but they suffer from noticeable artifacts.In this paper, we present a technique that combines forward rendering simulated features with deep-learning imagemanipulation to improve the rendering quality of splatting-style approaches to be perceptually similar to ray tracingsolutions, circumventing the cost, complexity, and limitations of exact fluid surface rendering by replacing it withthe flat cost of a neural network pass. Our solution is based on the idea of training generative deep neural networkswith image pairs consisting of cheap particle impostor renders and ground truth high quality ray-traced images.