Search Results for author:
Found 64 papers, 40 papers with code
Light Transport-aware Diffusion Posterior Sampling for Single-View Reconstruction of 3D Volumes
We introduce a single-view reconstruction technique of volumetric fields in which multiple light scattering effects are omnipresent, such as in clouds.
APEBench: A Benchmark for Autoregressive Neural Emulators of PDEs
We introduce the Autoregressive PDE Emulator Benchmark (APEBench), a comprehensive benchmark suite to evaluate autoregressive neural emulators for solving partial differential equations.
Flow Matching for Posterior Inference with Simulator Feedback
Flow-based generative modeling is a powerful tool for solving inverse problems in physical sciences that can be used for sampling and likelihood evaluation with much lower inference times than traditional methods.
ConFIG: Towards Conflict-free Training of Physics Informed Neural Networks
To improve learning the challenging multi-objective task posed by PINNs, we propose the ConFIG method, which provides conflict-free updates by ensuring a positive dot product between the final update and each loss-specific gradient.
The Unreasonable Effectiveness of Solving Inverse Problems with Neural Networks
In fact, neural networks trained to learn solutions to inverse problems can find better solutions than classical optimizers even on their training set.
Physics-embedded Fourier Neural Network for Partial Differential Equations
The MC-Fourier layer is by design translation- and rotation-invariant in the frequency domain, serving as a plug-and-play module that adheres to the laws of momentum conservation.
Stabilizing Backpropagation Through Time to Learn Complex Physics
Of all the vector fields surrounding the minima of recurrent learning setups, the gradient field with its exploding and vanishing updates appears a poor choice for optimization, offering little beyond efficient computability.
Symmetric Basis Convolutions for Learning Lagrangian Fluid Mechanics
Learning physical simulations has been an essential and central aspect of many recent research efforts in machine learning, particularly for Navier-Stokes-based fluid mechanics.
Differentiability in Unrolled Training of Neural Physics Simulators on Transient Dynamics
The accuracy of models trained in a fully differentiable setup differs compared to their non-differentiable counterparts.
Uncertainty-aware Surrogate Models for Airfoil Flow Simulations with Denoising Diffusion Probabilistic Models
As such, it can yield realistic and detailed samples from the distribution of solutions.
Physics-Preserving AI-Accelerated Simulations of Plasma Turbulence
Turbulence in fluids, gases, and plasmas remains an open problem of both practical and fundamental importance.
Benchmarking Autoregressive Conditional Diffusion Models for Turbulent Flow Simulation
We find that even simple diffusion-based approaches can outperform multiple established flow prediction methods in terms of accuracy and temporal stability, while being on par with state-of-the-art stabilization techniques like unrolling at training time.
Learning to Estimate Single-View Volumetric Flow Motions without 3D Supervision
Despite the complexity of this task, we show that it is possible to train the corresponding networks without requiring any 3D ground truth for training.
Solving Inverse Physics Problems with Score Matching
We propose to solve inverse problems involving the temporal evolution of physics systems by leveraging recent advances from diffusion models.
Exploring Physical Latent Spaces for High-Resolution Flow Restoration
We explore training deep neural network models in conjunction with physics simulations via partial differential equations (PDEs), using the simulated degrees of freedom as latent space for a neural network.
Guaranteed Conservation of Momentum for Learning Particle-based Fluid Dynamics
We present a novel method for guaranteeing linear momentum in learned physics simulations.
Wavelet-based Loss for High-frequency Interface Dynamics
As an alternative, we present a new method based on a wavelet loss formulation, which remains transparent in terms of what is optimized.
Control of Two-way Coupled Fluid Systems with Differentiable Solvers
We investigate the use of deep neural networks to control complex nonlinear dynamical systems, specifically the movement of a rigid body immersed in a fluid.
WeatherBench Probability: A benchmark dataset for probabilistic medium-range weather forecasting along with deep learning baseline models
WeatherBench is a benchmark dataset for medium-range weather forecasting of geopotential, temperature and precipitation, consisting of preprocessed data, predefined evaluation metrics and a number of baseline models.
Leveraging Stochastic Predictions of Bayesian Neural Networks for Fluid Simulations
We investigate uncertainty estimation and multimodality via the non-deterministic predictions of Bayesian neural networks (BNNs) in fluid simulations.
TemporalUV: Capturing Loose Clothing with Temporally Coherent UV Coordinates
We propose a novel approach to generate temporally coherent UV coordinates for loose clothing.
Half-Inverse Gradients for Physical Deep Learning
Recent works in deep learning have shown that integrating differentiable physics simulators into the training process can greatly improve the quality of results.
Simulating Liquids with Graph Networks
Simulating complex dynamics like fluids with traditional simulators is computationally challenging.
Learned Turbulence Modelling with Differentiable Fluid Solvers: Physics-based Loss-functions and Optimisation Horizons
In this paper, we train turbulence models based on convolutional neural networks.
Learning Similarity Metrics for Volumetric Simulations with Multiscale CNNs
Simulations that produce three-dimensional data are ubiquitous in science, ranging from fluid flows to plasma physics.
Scale-invariant Learning by Physics Inversion
We find that state-of-the-art training techniques are not well-suited to many problems that involve physical processes.
Autonomous Shaping of Latent-Spaces from Reduced PDEs for Physical Neural Networks
In contrast to previous work, we do not constrain the PDE solver but instead give the neural network complete freedom to shape the PDE solutions as degrees of freedom of a latent space.
Physics-based Deep Learning
This digital book contains a practical and comprehensive introduction of everything related to deep learning in the context of physical simulations.
Towards high-accuracy deep learning inference of compressible turbulent flows over aerofoils
The present study investigates the accurate inference of Reynolds-averaged Navier-Stokes solutions for the compressible flow over aerofoils in two dimensions with a deep neural network.
Self-Supervised Collision Handling via Generative 3D Garment Models for Virtual Try-On
We propose a new generative model for 3D garment deformations that enables us to learn, for the first time, a data-driven method for virtual try-on that effectively addresses garment-body collisions.
Global Transport for Fluid Reconstruction with Learned Self-Supervision
We propose a novel method to reconstruct volumetric flows from sparse views via a global transport formulation.
Frequency-aware Interface Dynamics with Generative Adversarial Networks
We present a new method for reconstructing and refining complex surfaces based on physical simulations.
Reviving Autoencoder Pretraining
The pressing need for pretraining algorithms has been diminished by numerous advances in terms of regularization, architectures, and optimizers.
ScalarFlow: A Large-Scale Volumetric Data Set of Real-world Scalar Transport Flows for Computer Animation and Machine Learning
In this paper, we present ScalarFlow, a first large-scale data set of reconstructions of real-world smoke plumes.
Neural Scene Graphs for Dynamic Scenes
Recent implicit neural rendering methods have demonstrated that it is possible to learn accurate view synthesis for complex scenes by predicting their volumetric density and color supervised solely by a set of RGB images.
Numerical investigation of minimum drag profiles in laminar flow using deep learning surrogates
In the present study, U-net based deep neural network (DNN) models are trained with high-fidelity datasets to infer flow fields, and then employed as surrogate models to carry out the shape optimisation problem, i. e. to find a drag minimal profile with a fixed cross-section area subjected to a two-dimensional steady laminar flow.
Fluid Dynamics
Purely data-driven medium-range weather forecasting achieves comparable skill to physical models at similar resolution
Numerical weather prediction has traditionally been based on physical models of the atmosphere.
Atmospheric and Oceanic Physics
Solver-in-the-Loop: Learning from Differentiable Physics to Interact with Iterative PDE-Solvers
Finding accurate solutions to partial differential equations (PDEs) is a crucial task in all scientific and engineering disciplines.
Data-driven Regularization via Racecar Training for Generalizing Neural Networks
We propose a novel training approach for improving the generalization in neural networks.
A Combined Data-driven and Physics-driven Method for Steady Heat Conduction Prediction using Deep Convolutional Neural Networks
For the data-driven based method, the introduction of physical equation not only is able to speed up the convergence, but also produces physically more consistent solutions.
Lagrangian Fluid Simulation with Continuous Convolutions
We present an approach to Lagrangian fluid simulation with a new type of convolutional network.
Latent Space Subdivision: Stable and Controllable Time Predictions for Fluid Flow
By selectively overwriting parts of the predicted latent space points, our proposed method is capable to robustly predict long-term sequences of complex physics problems.
Learning Similarity Metrics for Numerical Simulations
We propose a neural network-based approach that computes a stable and generalizing metric (LSiM) to compare data from a variety of numerical simulation sources.
WeatherBench: A benchmark dataset for data-driven weather forecasting
Data-driven approaches, most prominently deep learning, have become powerful tools for prediction in many domains.
Learning to Control PDEs with Differentiable Physics
Predicting outcomes and planning interactions with the physical world are long-standing goals for machine learning.
Learning Time-Aware Assistance Functions for Numerical Fluid Solvers
While our approach is very general and applicable to arbitrary partial differential equation models, we specifically highlight gains in accuracy for fluid flow simulations.
Sparse Surface Constraints for Combining Physics-based Elasticity Simulation and Correspondence-Free Object Reconstruction
In a number of tests using synthetic datasets and real-world measurements, we analyse the robustness of our approach and the convergence behavior of the numerical optimization scheme.
Graphics I.6
Stochastic Neural Physics Predictor
Recently, neural-network based forward dynamics models have been proposed that attempt to learn the dynamics of physical systems in a deterministic way.
Learning General and Reusable Features via Racecar-Training
We propose a novel training approach for improving the learning of generalizing features in neural networks.
Tranquil Clouds: Neural Networks for Learning Temporally Coherent Features in Point Clouds
Point clouds, as a form of Lagrangian representation, allow for powerful and flexible applications in a large number of computational disciplines.
Volumetric Isosurface Rendering with Deep Learning-Based Super-Resolution
With the advent of deep learning networks, a number of architectures have been proposed recently to infer missing samples in multi-dimensional fields, for applications such as image super-resolution and scan completion.
A Multi-Pass GAN for Fluid Flow Super-Resolution
We propose a novel method to up-sample volumetric functions with generative neural networks using several orthogonal passes.
Learning Temporal Coherence via Self-Supervision for GAN-based Video Generation
Additionally, we propose a first set of metrics to quantitatively evaluate the accuracy as well as the perceptual quality of the temporal evolution.
Ranked #1 on
Video Super-Resolution
on MSU Video Upscalers: Quality Enhancement
(VMAF metric)
Deep Learning Methods for Reynolds-Averaged Navier-Stokes Simulations of Airfoil Flows
With this study we investigate the accuracy of deep learning models for the inference of Reynolds-Averaged Navier-Stokes solutions.
Coupled Fluid Density and Motion from Single Views
We present a novel method to reconstruct a fluid's 3D density and motion based on just a single sequence of images.
Deep Fluids: A Generative Network for Parameterized Fluid Simulations
This paper presents a novel generative model to synthesize fluid simulations from a set of reduced parameters.
Latent-space Physics: Towards Learning the Temporal Evolution of Fluid Flow
We propose a method for the data-driven inference of temporal evolutions of physical functions with deep learning.
tempoGAN: A Temporally Coherent, Volumetric GAN for Super-resolution Fluid Flow
We propose a temporally coherent generative model addressing the super-resolution problem for fluid flows.
Data-Driven Synthesis of Smoke Flows with CNN-based Feature Descriptors
With the help of this patch advection, we generate stable space-time data sets from detailed fluids for our repositories.
Generating Liquid Simulations with Deformation-aware Neural Networks
Our algorithm captures these complex phenomena in two stages: a first neural network computes a weighting function for a set of pre-computed deformations, while a second network directly generates a deformation field for refining the surface.
Liquid Splash Modeling with Neural Networks
We use neural networks to model the regression of splash formation using a classifier together with a velocity modifier.
Primal-Dual Optimization for Fluids
While our method is generally applicable to many problems in fluid simulations, we focus on the two topics of fluid guiding and separating solid-wall boundary conditions.
Graphics I.6.8; I.3.7; G.1.6
Interpolations of Smoke and Liquid Simulations
We present a novel method to interpolate smoke and liquid simulations in order to perform data-driven fluid simulations.
Graphics I.6.8; I.3.7
SMASH: Physics-guided Reconstruction of Collisions from Videos
Authoring even two body collisions in the real world can be difficult, as one has to get timing and the object trajectories to be correctly synchronized.
