Explore @tum-pbs Open Source projects

TUM Physics-based Simulation (@tum-pbs)

tum-pbs

Stars
3,306
Global Org. Rank 6,459 (Top 3 %)
Followers 18
Registered almost 5 years ago
Most used languages

Python
61.5 %

Jupyter Notebook
23.1 %

C++
11.5 %

JavaScript
3.8 %
Location 🇩🇪 Germany
Country Total Rank 748
Country Ranking

Jupyter Notebook
21

Python
125

C++
1,186

JavaScript
2,878

PhiFlow

A differentiable PDE solving framework for machine learning

pbdl-book

Welcome to the Physics-based Deep Learning Book (v0.2)

Jupyter Notebook

Solver-in-the-Loop

Solver-in-the-Loop: Learning from Differentiable Physics to Interact with Iterative PDE-Solvers

PhiML

Intuitive scientific computing with dimension types for Jax, PyTorch, TensorFlow & NumPy

autoreg-pde-diffusion

Benchmarking Autoregressive Conditional Diffusion Models for Turbulent Flow Simulation

Jupyter Notebook

DMCF

Guaranteed Conservation of Momentum for Learning Particle-based Fluid Dynamics (NeurIPS '22)

Diffusion-based-Flow-Prediction

Official implementation of the AIAA Journal paper "Uncertainty-aware Surrogate Models for Airfoil Flow Simulations with Denoising Diffusion Probabilistic Models"

Jupyter Notebook

differentiable-piso

Code repository for "Learned Turbulence Modelling with Differentiable Fluid Solvers"

dl-surrogates

LSIM

LSiM is a learned metric to compute distance values for 2D data from numerical simulations

coord-trans-encoding

This is the source code for our paper "Towards high-accuracy deep learning inference of compressible turbulent flows over aerofoils"

CG-Solver-in-the-Loop

Conjugate Gradient related code for "Solver-in-the-Loop: Learning from Differentiable Physics to Interact with Iterative PDE-Solvers"

ConFIG

Official implementation of Conflict-Free Inverse Gradients Method

SMDP

Solving Inverse Physics Problems with Score Matching

Jupyter Notebook

Global-Flow-Transport

Repository for our CVPR 2021 Global Flow Transport Paper

half-inverse-gradients

Source code for the ICLR'22 paper on "Half-Inverse Gradients"

VOLSIM

VolSiM, a CNN-based metric to compute the similarity of 3D data from numerical simulations

SIP

Scale-invariant Learning by Physics Inversion (NeurIPS 2022)

DiffPhys-CylinderWakeFlow

Jupyter Notebook

StableBPTT

The source code the for the ICLR'24 paper "Stabilizing Backpropagation Through Time to Learn Complex Physics"

unrolling

reconstructScalarFlows

ScalarFlow Reconstruction for Large-Scale Volumetric Data Sets of Real-world Scalar Transport Flows

SFBC

ICLR'24: Symmetric basis convolutions for learning lagrangian fluid mechanics

Jupyter Notebook

racecar

Data-driven Regularization via Racecar Training for Generalizing Neural Networks

two-way-coupled-control

Neural-Global-Transport

Repository for the ICLR '23 paper on Neural-Global-Transport

Hybrid-Solver-for-Reactive-Flows