Fakultät Informatik

M.Sc. Marie-Lena Eckert, Research Associate and PhD Candidate

This website is no longer updated (July 2017). Have a look at our new  games engineering website or at my  LinkedIn profile!

I am part of the group around Prof. Nils Thuerey. My current research topic is reconstructing both 3D volume and 3D motion of real fluid phenomena with only a single 2D input video. Previously, I was working on separating boundary conditions for liquids based on convex optimization methods.

Topics of Research: fluid simulation, fluid capture, fluid tracking, convex optimization, numeric solvers, neural networks

I am organizing the exercises for the lecture "Deep Learning and Numerical Simulations for Visual Effects" and I have been supervising Bachelor's and Master's Theses, see below.

How to get in Touch




+49 89 289 19476


+49 89 289 19462




Technische Universität München
Informatik 15 (Computer Graphics, Games Engineering)
Boltzmannstrasse 3
85748 Garching bei München

Recent Publications

 A Primal-Dual Optimization for Fluids
T. Inglis*, M.-L. Eckert*, J. Gregson, N. Thuerey
Published in Computer Graphics Forum



Talks and Posters

"3D Reconstruction of Volume and Velocity of Real Fluid Phenomena Based on a Single Camera View", invited talk,  Prof. Matthias Teschner - Computer Graphics, Albert-Ludwigs-University Freiburg, May 2017

"Reconstructing Volume and Motion from Real Fluid Phenomena with a Minimal Number of Camera Views", poster presentation,  KAUST Research Conference: Visual Computing - Modeling and Reconstruction, April 2017

"Primal-Dual Optimization for Fluids", conference talk,  Eurographics, April 2017


Computers & Graphics Journal

Supervised Theses

"GPU-accelerated Stochastic Tomography for 3D Volume Reconstruction of Real Fluid Phenomena" - Tobias Kammerer, Master's Thesis, 2017 (in progress)

"Optimized Volume Reconstruction for Fluids with Non-Linear Lighting Models" - Tobias Gottwald, Master's Thesis, 2017

"Experimental Capture of Smoke and Evaluation of Volume Reconstruction Algorithms" - Florian Reichhold, Master's Thesis, 2016

"Reconstruction of Fluid Volumes Based on Stochastic Tomography" - Dominik Dechamps, Master's Thesis, 2016

"Modeling 3D Fluid Volumes Based on Appearance Transfer" - Christoph Pölt, Master's Thesis, 2015



Bachelor and Master thesis in the following areas:
- A remote rendering system for point cloud data (in collaboration with industry)

- Deep learning for improved weather forecasting

- Learning trajectory clustering using neural network
- Learning Level-of-Detail representations for point clouds

- In collaboration with partners from industry, we have a number of thesis topics available in the area of point-based rendering, geo-localization using public data, scene fusion from different viewpoints. If you are interested, please contact  westermann(at)tum.de


- One PhD position on   Turbulence Visualization is available at the Computer Graphics & Visualization group.