I finished my PhD in September’19 and started working at Weta Digital as Simulation Researcher. Check out my website and have a look at my LinkedIn profile!

My research topics included the improvement of realism and control of fluid simulations. We used the convex optimization technique fast first-order Primal-Dual method [PCBC09] for several complex problems, such as reconstructing both 3D volume and motion of real-world fluid phenomena based on 2D input sequences, which is the inverse problem to forward fluid simulation. We targeted accurate multi-view reconstructions from a sparse number of cameras, which we gather in our data set ScalarFlow, as well as single-view reconstructions. Furthermore, we developed a flexible fluid guiding method and achieved separating boundary conditions for liquids with a common CG solver.

Keywords: fluid simulation, fluid capture, fluid tracking, convex optimization, numeric solvers, neural networks

I have been organizing the exercises for the lectures “Basics: Algorithms and Data Structures” and “Deep Learning and Numerical Simulations for Visual Effects” as well as the seminar “Deep Learning in Physics”. Additionally, I have been supervising Bachelor’s and Master’s Theses, see below.

How to get in Touch

  • eMail: ml (at) marielenaeckert.com [or marie-lena.eckert (at) tum.de]
  • Phone: +49.89.289.19476
  • Fax: +49 89 289 19462
  • Room: 02.13.061

ScalarFlow

also presented as two minutes papers

Publications

     
  Marie-Lena Eckert, Kiwon Um, Nils Thuerey, “ScalarFlow: A Large-Scale Volumetric Data Set of Real-world Scalar Transport Flows for Computer Animation and Machine Learning“, ACM Transactions on Graphics (SIGGRAPH Asia 2019). ScalarFlow is found here.
     
  Marie-Lena Eckert, Wolfgang Heidrich, Nils Thuerey, “Coupled Fluid Density and Motion from Single Views“, CGF Volume 37 (2018), Issue 8, p. 47-58; best paper award from SCA’18
        
  Tiffany Inglis*, Marie-Lena Eckert*, James Gregson, Nils Thuerey, “Primal-Dual Optimization for Fluids“, CGF Volume 36 (2017), Issue 8, p. 354–368
        
  Marie-Lena Eckert, Neslihan Kose, Jean-Luc Dugelay, “Facial cosmetics database and impact analysis on automatic face recognition“, MMSP 2013: 434-439
        
   Marie-Lena Eckert, Andreas Freitag, Florian Matthes, Sascha Roth, Christopher Schulz, “Decision Support for Selecting an Application Landscape Integration Strategy in Mergers and Acquisitions“, ECIS 2012: 88

Theses

Marie-Lena Eckert, “Optimization for Fluid Simulation and Reconstruction of Real-World Flow Phenomena“, Ph.D. Thesis, Technical University of Munich, September 2019.
  Marie-Lena Eckert, “Flexible Boundary Conditions in Fluid Solvers Based on Proximal Operators“, M.Sc. Thesis, Technical University of Munich, November 2014.

Talks and Posters

ScalarFlow: A Large-Scale Volumetric Data Set of Real-world Scalar Transport Flows for Computer Animation and Machine Learning“, conference presentation, SIGGRAPH Asia, November 2019

Coupled Fluid Density and Motion from Single Views“, conference presentation, SCA, July 2018

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 presentation, Eurographics, April 2017

Reviews

SIGGRAPH, SIGGRAPH Asia, Computer & Graphics Journal (CAG)

Teaching

Supervised Theses

Learning to Reconstruct Smoke Volumes from Images” – Daniel Frejek, Master’s Thesis, 2019

Improving a Low-Cost Capturing Process for Reconstructing Volume and Motion of Real Fluid Phenomena” – Daniel Frejek, Guided Research, 2017

Capturing Real Fluid Phenomena with Raspberry Pi Cameras” – Florian Alkofer, Bachelor’s Thesis, 2017

GPU-accelerated Stochastic Tomography for 3D Volume Reconstruction of Real Fluid Phenomena” – Tobias Kammerer, Master’s Thesis, 2017

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


[PCBC09] POCK T., CREMERS D., BISCHOF H., CHAMBOLLE A.: An algorithm for minimizing the mumford-shah functional. In Proceedings of IEEE International Conference on Computer Vision (2009).