My research involves computer graphics, real-time rendering, numerical simulation and Deep Learning. Currently, I’m working on a PISO fluid solver in PyTorch. Previously, I’ve worked on 3D smoke reconstruction from video using differentiable rendering.

Since October 2019 I’m a Ph.D. candidate in Nils Thuerey’s group after recieving my M.Sc. and B.Sc. degrees in Informatics: Games Engineering at TUM.

Contact

E-mail: erik.franz (at) tum.de
Room: 02.13.055

Publications

  • E. Franz, B. Solenthaler and N. Thuerey, “Learning to Estimate Single-View Volumetric Flow Motions without 3D Supervision”, ICLR 2023 ☛ [Project]
  • M. Chu et al., “Physics informed neural fields for smoke reconstruction with sparse data”, SIGGRAPH 2022 ☛ [Paper]
  • E. Franz, B. Solenthaler and N. Thuerey, “Global Transport for Fluid Reconstruction with Learned Self-Supervision”, CVPR 2021 ☛ [Project]
  • Y. Xie* , E. Franz* and M. Chu* and N. Thuerey, “tempoGAN: A Temporally Coherent, Volumetric GAN for Super-resolution Fluid Flow”, SIGGRAPH 2018, (*Similar contributions) ☛ [Project]

Theses

  • Erik Franz, “Deep-Learning based Super-Resolution for Games”, M.Sc. Thesis, Technische Universität München, August 2019. (English)
  • Erik Franz, “Synthesizing Smoke Datasets with Generative Adversarial Networks”, B.Sc. Thesis, Technische Universität München, August 2017. (English)

Teaching