I am currently a postdoctoral researcher at Kyoto University Computer Vision Lab. My research interests include physics-based vision, multi-view geometry, and inverse rendering.

Education

  • Kyoto University, 2015-2024
    • Ph.D. in Informatics, 2024
    • Master in Informatics, 2021
    • Bachelor in Engineering, 2019

Publications

Google Scholar

  • Correspondences of the Third Kind: Camera Pose Estimation from Object Reflection
    K. Yamashita, V. Lepetit, and K. Nishino,
    in Proc. of European Conference on Computer Vision ECCV’24, Oct., 2024. [oral].
    [ paper ][ supp. PDF ][ project ][ code/data ]

  • DeepShaRM: Multi-View Shape and Reflectance Map Recovery Under Unknown Lighting
    K. Yamashita, S. Nobuhara, and K. Nishino,
    in Proc. of International Conference on 3D Vision (3DV), 2024.
    [ arXiv ]

  • nLMVS-Net: Deep Non-Lambertian Multi-View Stereo
    K. Yamashita, Y. Enyo, S. Nobuhara, and K. Nishino,
    in IEEE/CVF Winter Conference on Applications of Computer Vision WACV’23, 2023.
    [ arXiv ][ link ][ code/data ]

  • 3D-GMNet: Single-View 3D Shape Recovery as A Gaussian Mixture
    K. Yamashita, S. Nobuhara, and K. Nishino,
    in Proc. of British Machine Vision Conference BMVC’20, Sep., 2020.
    [ arXiv ][ link ]

Hobby

I make robots as a hobby. I have been participating in Micromouse, a competition for autonomous and self-contained mobile robots.

In 2019, I won a New Technology Prize in All Japan Micromouse Contest by making a line-following robot run an optimized, faster path.