Simulating turbulent flows is crucial for a wide range of applications, ...
We address the challenging problem of jointly inferring the 3D flow and
...
Diffusion models based on stochastic differential equations (SDEs) gradu...
We explore training deep neural network models in conjunction with physi...
We present a novel method for guaranteeing linear momentum in learned ph...
Generating highly detailed, complex data is a long-standing and frequent...
We investigate the use of deep neural networks to control complex nonlin...
We investigate uncertainty estimation and multimodality via the
non-dete...
WeatherBench is a benchmark dataset for medium-range weather forecasting...
We propose a novel approach to generate temporally coherent UV coordinat...
Recent works in deep learning have shown that integrating differentiable...
Simulating complex dynamics like fluids with traditional simulators is
c...
In this paper, we train turbulence models based on convolutional neural
...
Simulations that produce three-dimensional data are ubiquitous in scienc...
Solving inverse problems, such as parameter estimation and optimal contr...
This digital book contains a practical and comprehensive introduction of...
The present study investigates the accurate inference of Reynolds-averag...
We propose a new generative model for 3D garment deformations that enabl...
We propose a novel method to reconstruct volumetric flows from sparse vi...
Recent implicit neural rendering methods have demonstrated that it is
po...
In this paper, we present ScalarFlow, a first large-scale data set of
re...
This paper proposes a novel framework to evaluate fluid simulation metho...
We propose a novel training approach for improving the generalization in...
Finding accurate solutions to partial differential equations (PDEs) is a...
With several advantages and as an alternative to predict physics field,
...
We propose an end-to-end trained neural networkarchitecture to robustly
...
We propose a neural network-based approach that computes a stable and
ge...
Data-driven approaches, most prominently deep learning, have become powe...
Predicting outcomes and planning interactions with the physical world ar...
We address the problem to infer physical material parameters and boundar...
Rendering an accurate image of an isosurface in a volumetric field typic...
We propose a novel method to up-sample volumetric functions with generat...
Adversarial training has been highly successful in the context of image
...
With this study we investigate the accuracy of deep learning models for ...
We present a novel method to reconstruct a fluid's 3D density and motion...
This paper presents a novel generative model to synthesize fluid simulat...
Our work explores methods for the data-driven inference of temporal
evol...
We propose a temporally coherent generative model addressing the
super-r...
We present a novel data-driven algorithm to synthesize high-resolution f...
Liquids exhibit highly complex, non-linear behavior under changing simul...
This paper proposes a new data-driven approach for modeling detailed spl...
We apply a novel optimization scheme from the image processing and machi...
We present a novel method to interpolate smoke and liquid simulations in...
Collision sequences are commonly used in games and entertainment to add ...