Junhong Min’s homepage
I work on 3D vision and robotic perception for reliable automation. I am a Principal Engineer at Samsung Electronics, where I develop stereo matching, depth estimation, and 6-DoF object pose estimation methods for industrial robot systems.
My recent research focuses on robust stereo depth estimation in difficult scenes, including transparent, reflective, and cluttered industrial environments. Earlier work studied computational imaging for super-resolution microscopy and low-dose CT reconstruction.
Across these projects, my interest is in perception methods that remain useful outside clean laboratory settings: accurate enough for research benchmarks, but also practical enough to support real robotic systems.
Featured Publications
- DepthFocus: Controllable Depth Estimation for See-Through Scenes, CVPR 2026. Paper / Project
- S²M²: Scalable Stereo Matching Model for Reliable Depth Estimation, ICCV 2025. Paper / Project / Code
- Confidence Aware Stereo Matching for Realistic Cluttered Scenario, ICIP 2024. Paper
- Sim-to-real Object Pose Estimation for Random Bin Picking, ICRA 2024. Paper
View full publication list / View patents
Latest News
Apr 2026: Won the CVPR NTIRE 2026 stereo track for HR depth from specular and transparent surfaces.
Feb 2026: Our paper, “DepthFocus: Controllable Depth Estimation for See-Through Scenes” was accepted to The IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2026!
Oct 2025: Our paper, “S²M²: Scalable Stereo Matching Model for Reliable Depth Estimation” was accepted to the International Conference on Computer Vision (ICCV) 2025!