Minjun Kang
About me
I am a Ph.D. student co-advised by Prof. Kuk-Jin Yoon and Prof. In So Kweon. I obtained my B.S. from Yonsei University (2019) and M.S. from KAIST (2021).
Previously, My research focused on low-level vision including facial / scene 3D reconstruction using a single image from dual-pixel. Recently, I have been working on 4D motion understanding of humans and making photorealistic avatars. Ultimately, my long-term goal is to create a realistic virtual AI character that can interact together with people.
Education
Ph.D. candidate in Robotics, KAIST
Mar. 2021 - PresentM.S. in Electrical Engineering, KAIST
Mar. 2019 - Feb. 2021B.S. in Electrical and Electronic Engineering, Yonsei University
Mar. 2015 - Feb. 2019
Publication
Stable Surface Regularization for Fast Few-Shot NeRF
Byeongin Joung, Byeong-Uk Lee, Jaesung Choe, Ukcheol Shin, Minjun Kang, Taeyeop Lee, In So Kweon, and Kuk-Jin Yoon
International Conference on 3D Vision (3DV), 2024.
[Paper]
Facial Depth and Normal Estimation using Single Dual-Pixel Camera
Minjun Kang, Jaesung Choe, Hyowon Ha, Hae-Gon Jeon, Sunghoon Im, In So Kweon, and Kuk-Jin Yoon
European Conference on Computer Vision (ECCV), 2022.
[Paper] [Code] [Video] [Slide]
@inproceedings{kang2022facial,
title={Facial depth and normal estimation using single dual-pixel camera},
author={Kang, Minjun and Choe, Jaesung and Ha, Hyowon and Jeon, Hae-Gon and Im, Sunghoon and Kweon, In So and Yoon, Kuk-Jin},
booktitle={European Conference on Computer Vision},
pages={181--200},
year={2022},
organization={Springer}
}
CMSNet: Deep Color and Monochrome Stereo
Hae-Gon Jeon, Sunghoon Im, Jaesung Choe, Minjun Kang, Joon-Young Lee, and Martial Hebert
International Journal of Computer Vision (IJCV), 2022.
[Paper]
@article{jeon2022cmsnet,
title={CMSNet: Deep Color and Monochrome Stereo},
author={Jeon, Hae-Gon and Im, Sunghoon and Choe, Jaesung and Kang, Minjun and Lee, Joon-Young and Hebert, Martial},
journal={International Journal of Computer Vision},
volume={130},
number={3},
pages={652--668},
year={2022},
publisher={Springer}
}
Volumefusion: Deep depth fusion for 3d scene reconstruction
Jaesung Choe, Sunghoon Im, Francois Rameau, Minjun Kang, and In So Kweon
IEEE International Conference on Computer Vision (ICCV), 2021.
[Paper] [Video] [Slide]
@inproceedings{choe2021volumefusion,
title={Volumefusion: Deep depth fusion for 3d scene reconstruction},
author={Choe, Jaesung and Im, Sunghoon and Rameau, Francois and Kang, Minjun and Kweon, In So},
booktitle={Proceedings of the IEEE/CVF International Conference on Computer Vision},
pages={16086--16095},
year={2021}
}
Activities
Reviewer at ICCV23, ECCV24, ACCV24