Nathan Louis

profile.jpg

I am a research engineer at Southwest Research Institute, specializing in AI-applied human biomechanics research. My current interest involves understanding the dynamics of human motion though vision and physics simulation.

I completed my Ph.D. at the University of Michigan, Ann Arbor under the guidance of Jason J. Corso. My graduate research was focused on extracting physically grounded information from video and relating it to quantifiable skill. This ranges from tracking hand and human body poses, estimating external forces from human motion, and ranking the quality of actions.

selected publications

  1. teaser_physical_plausibility.jpg
    Measuring Physical Plausibility of 3D Human Poses Using Physics Simulation
    Nathan Louis, Mahzad Khoshlessan, and Jason J Corso
    British Machine Vision Conference, 2024
  2. teaser_super_resolution.png
    Super-resolution of clinical CT: Revealing microarchitecture in whole bone clinical CT image data
    Lance L Frazer, Nathan Louis, Wojciech Zbijewski, and 3 more authors
    Bone, 2024
  3. teaser_temporally_guided.jpg
    Temporally guided articulated hand pose tracking in surgical videos
    Nathan Louis, Luowei Zhou, Steven J Yule, and 5 more authors
    International Journal of Computer Assisted Radiology and Surgery, 2023
  4. teaser_external_forces.png
    Learning to estimate external forces of human motion in video
    Nathan Louis, Jason J Corso, Tylan N Templin, and 2 more authors
    In Proceedings of the 30th ACM International Conference on Multimedia, 2022
  5. teaser_weakly_supervised.png
    Weakly-supervised video object grounding from text by loss weighting and object interaction
    Luowei Zhou, Nathan Louis, and Jason J Corso
    British Machine Vision Conference, 2018