Byungsoo Kim

Senior Software Engineer | Generative AI Technology, NVIDIA

prof_pic.jpg

I am currently a Senior Software Engineer developing Generative AI Technology at NVIDIA. I received my joint PhD from Computer Graphics Lab at ETH Zurich and Disney Research, under the supervision of Prof. Markus Gross and Prof. Barbara Solenthaler. My research interests span machine learning for physics-based simulation and visual computing.

News

Jul 14, 2024 I’m super excited to share that our paper, “Deep Fluids: A Generative Network for Parameterized Fluid Simulations”, has been selected as a recipient of the 2024 Frontiers of Science Award at the International Congress of Basic Science.
Jul 11, 2024 Our paper “Near-realtime Facial Animation by Deep 3D Simulation Super-Resolution” is published at ACM Transactions on Graphics.
Jul 1, 2024 Our paper “Study on Morphometrical Urban Aerodynamic Roughness Multi-Scale Exploration Using LiDAR Remote Sensing” is published at Remote Sensing.
Jan 16, 2024 I am thrilled to share that I, along with Vinicius C. Azevedo, Raphael Ortiz, and Paul Kanyuk, have been nominated for a VES Award in the Emerging Technology category for our collaborative work on Elemental - Volumetric Neural Style Transfer.
Aug 9, 2023 Our ML Hair and NeuralVDB are featured in Omniverse SIGGRAPH 2023 Demo.
Jul 7, 2023 I gave a talk at POSTECH hosted by Prof. Jisung Park.
Jun 22, 2023 ETH Zurich posted an article about our technology used in “Elemental”.
Mar 5, 2023 An animation film “Elemental” by Pixar is released where our Neural Flow Stylization technique is used. Check out this post!
Dec 13, 2022 Our paper “Physics-Informed Neural Corrector for Deformation-based Fluid Control” is conditionally accepted to Eurographics 2023.
Aug 16, 2022 I joined Simulation Technology Team at NVIDIA led by Ken Museth.

More ...

Publications

  1. Near-realtime Facial Animation by Deep 3D Simulation Super-Resolution
    Hyojoon Park, Sangeetha Grama Srinivasan, Matthew Cong, and 5 more authors
    ACM Trans. Graph., Jul 2024.
  2. Study on Morphometrical Urban Aerodynamic Roughness Multi-Scale Exploration Using LiDAR Remote Sensing
    Seung Man An, Byungsoo Kim, Chaeyeon Yi, and 3 more authors
    Remote Sensing, 2024.
  3. Physics-Informed Neural Corrector for Deformation-based Fluid Control
    Jingwei Tang, Byungsoo Kim, Vinicius C. Azevedo, and 1 more author
    Computer Graphics Forum (Proc. EUROGRAPHICS), May 2023.
  4. Implicit Neural Representation for Physics-Driven Actuated Soft Bodies
    Lingchen Yang, Byungsoo Kim, Gaspard Zoss, and 3 more authors
    ACM Trans. Graph. (Proc. SIGGRAPH), Jul 2022. (Honorable Mention)
  5. Deep Reconstruction of 3D Smoke Densities from Artist Sketches
    Byungsoo Kim, Xingchang Huang, Laura Wuelfroth, and 4 more authors
    Computer Graphics Forum (Proc. EUROGRAPHICS), May 2022.
  6. Deep Learning Speeds Up Ice Flow Modelling by Several Orders of Magnitude
    Guillaume Jouvet, Guillaume Cordonnier, Byungsoo Kim, and 3 more authors
    Journal of Glaciology, Dec 2021.
  7. Modeling Electromagnetic Navigation Systems
    Samuel L. Charreyron, Quentin Boehler, Byungsoo Kim, and 3 more authors
    IEEE Transactions on Robotics, Jan 2021.
  8. Data-Driven Methods for Artist-Directed Fluid Simulations
    Byungsoo Kim
    Doctoral Thesis. ETH Zurich. 2020.
  9. Latent Space Subdivision: Stable and Controllable Time Predictions for Fluid Flow
    Steffen Wiewel, Byungsoo Kim, Vinicius C. Azevedo, and 2 more authors
    Computer Graphics Forum (Proc. SCA), Nov 2020.
  10. Lagrangian Neural Style Transfer for Fluids
    Byungsoo Kim, Vinicius C. Azevedo, Markus Gross, and 1 more author
    ACM Trans. Graph. (Proc. SIGGRAPH), Jul 2020.
  11. Neural Smoke Stylization with Color Transfer
    Fabienne Christen, Byungsoo Kim, Vinicius C. Azevedo, and 1 more author
    In Eurographics 2020 - Short Papers, May 2020.
  12. Frequency-Aware Reconstruction of Fluid Simulations with Generative Networks
    Simon Biland, Vinicius C. Azevedo, Byungsoo Kim, and 1 more author
    In Eurographics 2020 - Short Papers, May 2020.
  13. Transport-Based Neural Style Transfer for Smoke Simulations
    Byungsoo Kim, Vinicius C. Azevedo, Markus Gross, and 1 more author
    ACM Trans. Graph. (Proc. SIGGRAPH Asia), Nov 2019.
  14. Robust Reference Frame Extraction from Unsteady 2D Vector Fields with Convolutional Neural Networks
    Byungsoo Kim, and Tobias Günther
    Computer Graphics Forum (Proc. EUROVIS), Jul 2019.
  15. Deep Fluids: A Generative Network for Parameterized Fluid Simulations
    Byungsoo Kim, Vinicius C. Azevedo, Nils Thuerey, and 3 more authors
    Computer Graphics Forum (Proc. EUROGRAPHICS), Jun 2019.
  16. Semantic Segmentation for Line Drawing Vectorization Using Neural Networks
    Byungsoo Kim, Oliver Wang, A. Cengiz Öztireli, and 1 more author
    Computer Graphics Forum (Proc. EUROGRAPHICS), May 2018.
  17. Learning Structured Representations for Geometry
    Byungsoo Kim
    Master Thesis. ETH Zurich. 2016.
  18. Previous Works
    Byungsoo Kim
    2008 - 2014.