Junho Lee



I am a PhD student at the 3D Vision Lab, part of the Department of Electrical and Computer Engineering at Seoul National University, where I work on 3D vision based robotic manipulation of transparent and specular objects. My PhD advisor is Young Min Kim.

My research goal is to build a robotic system that can robustly perceive and manipulate visually confounding real-world objects. Specifically, I focus on manipulating transparent objects with a robot arm. Currently, I am working on grasping such objects via neural fields while obtaining input from an RGB-D camera.

CV  /  GitHub  /  Linkedin  /  Google Scholar  

profile photo

News


  • Nov. 2023: One paper got accepted to RA-L
  • Jun. 2022: One paper got accepted to IROS 2022
  • Sept. 2020: Joined 3D Vision Lab @ SNU
  • Sept. 2020: Earned Bachelor's degree in Electrical and Computer Engineering @ SNU

Publications

NFL: Normal Field Learning for 6-DoF Grasping of Transparent Objects
Junho Lee, Sang Min Kim, Yonghyeon Lee, and Young Min Kim
IEEE Robitics and Automation Letters (RA-L), 2023
paper video code project page

MasKGrasp: Mask-based Grasping for Scenes with Multiple General Real-world Objects
Junho Lee, Junhwa Hur, Inwoo Hwang, and Young Min Kim
IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2022
paper video

GATSBI: Generative Agent-centric Spatio-temporal Object Interaction
Cheol-Hui Min, Jinseok Bae, Junho Lee, and Young Min Kim
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2021, Oral
paper video


Education


  • Seoul National University, Seoul, Korea Sep.2020 - Present M.S./Ph.D. in Electrical and Computer Engineering
  • Seoul National University, Seoul, Korea Mar.2017 - Aug.2020 B.S. in Electrical and Computer Engineering

Honors and Awards


  • Tutor awards by SNU College of Engineering 2021

Patents


  • KR10-2596914

Academic Activities


  • Reviewer: RA-L, IROS

Design and source code from Jon Barron's website
Jekyll template from Leonid Keselman's website