Spatio-Temporal Methods for Data-driven Computer Animation and Simulation

Project Information

SpaTe

Grant agreement ID: 863850

DOI

10.3030/863850

Project closed

EC signature date 13 February 2020

Start date 1 September 2020

End date 31 August 2025

Funded under

• EXCELLENT SCIENCE - European Research Council (ERC)

Total cost

€ 1 998 750,00

EU contribution

€ 1 998 750,00

Coordinated by

TECHNISCHE UNIVERSITAET MUENCHEN
Germany

CORDIS provides links to public deliverables and publications of HORIZON projects.

Links to deliverables and publications from FP7 projects, as well as links to some specific result types such as dataset and software, are dynamically retrieved from OpenAIRE .

Publications

Conference proceedings (4)

Guaranteed Conservation of Momentum for Learning Particle-based Fluid Dynamics

Author(s): Lukas Prantl, Benjamin Ummenhofer, Vladlen Koltun, Nils Thuerey
Published in: Advances in Neural Information Processing, Issue 1, 2022
Publisher: NeurIPS

Half-Inverse Gradients for Physical Deep Learning

Author(s): Patrick Schnell, Philipp Holl, Nils Thuerey
Published in: ICLR, Issue 2022, 2022, Page(s) 1-22
Publisher: ICLR

Solving Inverse Physics Problems with Score Matching

Author(s): Benjamin Holzschuh, Simona Vegetti, Nils Thuerey
Published in: Advances in Neural Information Processing Systems, Issue 36, 2023, Page(s) -
Publisher: Advances in Neural Information Processing Systems
DOI: 10.48550/arxiv.2301.10250

Global Transport for Fluid Reconstruction with Learned Self-Supervision

Author(s): Erik Franz; Barbara Solenthaler; Nils Thuerey
Published in: CVPR, Issue 1, 2021
Publisher: CVPR
DOI: 10.1109/cvpr46437.2021.00168

Peer reviewed articles (8)

Unsteady cylinder wakes from arbitrary bodies with differentiable physics-assisted neural network

Author(s): Shuvayan Brahmachary, Nils Thuerey
Published in: Physical Review E, Issue 109, 2024, ISSN 2470-0045
Publisher: American Physical Society
DOI: 10.1103/physreve.109.055304

Reviving autoencoder pretraining

Author(s): You Xie; Nils Thuerey
Published in: Neural Computing and Applications, Issue 35, 2022, ISSN 0941-0643
Publisher: Springer Verlag
DOI: 10.1007/s00521-022-07892-0

Deep learning-based predictive modeling of transonic flow over an airfoil

Author(s): Liwei Chen, Nils Thuerey
Published in: Physics of Fluids, Issue 36, 2024, ISSN 1070-6631
Publisher: American Institute of Physics
DOI: 10.1063/5.0238413

Realistic galaxy images and improved robustness in machine learning tasks from generative modelling

Author(s): Benjamin J Holzschuh, Conor M O’Riordan, Simona Vegetti, Vicente Rodriguez-Gomez, Nils Thuerey
Published in: Monthly Notices of the Royal Astronomical Society, Issue 515, 2024, Page(s) 652-677, ISSN 0035-8711
Publisher: Blackwell Publishing Inc.
DOI: 10.1093/mnras/stac1188

Differentiability in unrolled training of neural physics simulators on transient dynamics

Author(s): Bjoern List, Li-Wei Chen, Kartik Bali, Nils Thuerey
Published in: Computer Methods in Applied Mechanics and Engineering, Issue 433, 2024, Page(s) 117441, ISSN 0045-7825
Publisher: Elsevier BV
DOI: 10.1016/j.cma.2024.117441

Learned turbulence modelling with differentiable fluid solvers: physics-based loss functions and optimisation horizons

Author(s): Björn List; Li-Wei Chen; Nils Thuerey
Published in: Crossref, Issue 1, 2022, ISSN 0022-1120
Publisher: Cambridge University Press
DOI: 10.1017/jfm.2022.738

Towards high-accuracy deep learning inference of compressible flows over aerofoils

Author(s): Li-Wei Chen; Nils Thuerey
Published in: Crossref, Issue 1, 2022, ISSN 0022-1120
Publisher: Cambridge University Press
DOI: 10.1016/j.compfluid.2022.105707

Learning Similarity Metrics for Volumetric Simulations with Multiscale CNNs

Author(s): Georg Kohl, Li-Wei Chen, Nils Thuerey
Published in: Proceedings of the AAAI Conference on Artificial Intelligence, Issue 37, 2023, Page(s) 8351-8359, ISSN 2374-3468
Publisher: Association for the Advancement of Artificial Intelligence
DOI: 10.1609/aaai.v37i7.26007