Mengyu (Rachel) Chu · 楚梦渝

Biography

I am a tenure-track Assistant Professor at the School of Intelligence Science and Technology at Peking University. Currently, I am affiliated with the Visual Computing and Learning Lab, collaborating with Prof. Baoquan Chen, Prof. Libin Liu, and Dr. Bin Wang.
From 2020 to 2022, I held the position of Lise Meitner Postdoctoral Research Fellow at Max Planck Institute for Informatics, where I was supervised by Prof. Christian Theobalt and Dr. Rhaleb Zayer. During this time, I worked within groups D6 (Visual Computing and Artificial Intelligence) and D4 (Computer Graphics).
Prior to that, I pursued my Ph.D. under the guidance of Prof. Nils Thuerey in the group at the Technical University of Munich from 2014 to 2020.
I completed my M.Eng. degree at Zhejiang University, China, in March 2014.

Research Interest

I'm interested in Physics-Enhanced Deep Learning. Combining deep-learning-based algorithms and physical simulations, the research aims to improve the flexibility of simulations and to enhance the accuracy and generalizability of deep learning models.


For Fluid Reconstruction

Y. Wang, S. Tang, and M. Chu. "Physics-Informed Learning of Characteristic Trajectories for Smoke Reconstruction", ACM SIGGRAPH 2024 Conference Papers

M. Chu, L. Liu, Q. Zheng, E. Franz, HP. Seidel, C. Theobalt, and R. Zayer. "Physics Informed Neural Fields for Smoke Reconstruction with Sparse Data", ACM Transactions on Graphics (SIGGRAPH 2022)

For Fluid Manipulation

M. Chu, N. Thuerey, HP. Seidel, C. Theobalt, and R. Zayer. "Learning Meaningful Controls for Fluids", ACM Transactions on Graphics (SIGGRAPH 2021)

For Video Synthesis

M. Chu, Y. Xie*, J. Mayer, L. Leal-Taixé and N. Thuerey. "Learning Temporal Coherence via Self-Supervision for GAN-based Video Generation", ACM Transactions on Graphics (SIGGRAPH 2020)


For Fluid Synthesis

Y. Xie, E. Franz, M. Chu and N. Thuerey. "TempoGAN: A Temporally Coherent, Volumetric GAN for Super-resolution Fluid Flow", ACM Transactions on Graphics (SIGGRAPH 2018)

Mengyu Chu and Nils Thuerey. "Data-Driven Synthesis of Smoke Flows with CNN-based Feature Descriptors", ACM Transactions on Graphics (SIGGRAPH 2017)


Others

  • M. Werhahn, Y. Xie, M. Chu and N. Thuerey. "A Multi-Pass GAN for Fluid Flow Super-Resolution", Proc. ACM Comput. Graph. Interact. Tech. 2 (2), 10:1--10:21 (SCA 2019)
  • S. Weiss, M. Chu, N. Thuerey and R. Westermann. "Volumetric isosurface rendering with deep learning-based super-resolution" IEEE Transactions on Visualization and Computer Graphics 27 (6), 3064-3078, 2021.
  • N. Kang, M. Chu, N. Thuerey, H.E. Lee, D. SAGONG "Method and apparatus for modeling smoke turbulence based on patch" US Patent 10261976

Education


2020.3-2022.5, Postdoctoral Research Fellow, Computer Science

Max Planck Institute for Informatics, Germany

2014.5-2020.2, Ph.D., Computer Science

Technical University of Munich, Germany


2011-2014, M.Eng, Computer Science and Technology

Zhejiang University, China

2007-2011, B.Eng, Software Engineering

Southeast University, China

Awards


2020, Ph.D. with Summa Cum Laude

Technical University of Munich


2020, Lise Meitner Postdoctoral Research Fellowship

Max Planck Institute for Informatics

  • Contact

    Email: mchu@pku.edu.cn
    Address: Sciences II Building, Office 2214S, Summer Palace Road No. 5, Haidian District, Beijing, China. (北京市海淀区颐和园路5号 北京大学理科2号楼2214S)