I am a 3rd year Ph.D. student in the Robotics Institute at Carnegie Mellon University, under the supervision of Yaser Sheikh. Before joining CMU, I spent three years as a researcher at ETRI, a government-funded research organization in Korea. I received my M.S. in Electrical Engineering and B.S. in Computer Science, both
from KAIST, Korea. The Samsung Scholarship is supporting my graduate study.
My main research interests are in computer vision, computer graphics, and machine perception of social behavior. My work focuses on analyzing and understanding dynamic scenes using more than 500 synchronized cameras (a.k.a. the Panoptic Studio).
Virtural Hanbyul in the Panoptic Studio
MAP Visibility Estimation for Large-Scale Dynamic 3D Reconstruction
Hyun Soo Park,
and Yaser Sheikh
In CVPR 2014 (Oral)
[Project Page] [Dataset]
Graph-based Shape Matching for Deformable Objects
Yekeun Jeong, Olivier Duchenne, and In So Kweon
In ICIP 2011
Graph-Based Robust Shape Matching for Robotic Application
Yekeun Jeong, Olivier Duchenne, Seong-Young Ko, and In So Kweon
In ICRA 2009
Statistical Background Subtraction Based on the Exact Per-pixel Distributions
Youngbae Hwang, Hanbyul Joo, Jun-sik Kim, and In So Kweon
In IAPR workshop on Machine Vision Applications (MVA) 2007
"The Panoptic Studio", People Image Analysis Consortium, CMU, Nov 2014.
"The Panoptic Studio", Reality Computing Meetup, Autodesk, Nov 2014.
"MAP Visibility Estimation for Large-Scale Dynamic 3D Reconstruction", CVPR, June 2014.
- Future Tech: Panoptic Studio, Daily Planet, Discovery Channel Canada, 2015
(TV show, in the linked website, click "Segments" and select "Future tech: Panoptic Studio")
- Freezing Memories in Time: Carnegie Mellon's amazing 3-D "Panoptic Studio", Slate, 2014 (Video)
- Tomorrow Daily: New video capture tech, the Rickroll 'Rickmote,' a new X-wing, and more, CNet, 2014 (Video)
- Camera-Studded Dome Tracks Your Every Move With Precision, NBCNews, 2014
- Camera-Filled Dome Recreates Full 3-D Motion Scenes, IEEE Spectrum, 2014
- Amazing 3-D Flicks from Dome of 500 Cameras?, Discovery News, 2014
- A Dome Packed With 480 Cameras Captures Detailed 3D Images In Motion, Gizmodo, 2014
- Scientists build a real Panopticon that captures your every move in 3D The Verge
- Hundreds of videos used to reconstruct 3-D motion without markers, ScienceDaily, 2014
- Researchers combine hundreds of videos to reconstruct 3D motion without markers, Phys.org, 2014
- Watch a dome full of cameras capture 3D motion in extreme detail, Engadget, 2014
- Researchers Use a 480-Camera Dome to More Accurately Capture 3D Motion PetaPixel, 2014
- Camera-studded dome used to reconstruct 3D motion, Gizmag, 2014
- Boffins fill a dome with 480 cameras for 3D motion capture Register, 2014
- 3D motion captured without markers, The Engineer, 2014
- Carnegie Mellon Packs 480 Cameras In A Dome To Perfectly Track 3D Motion, Popular Photography, 2014
- Carnegie Mellon Combines Hundreds of Videos To Reconstruct 3D Motion Without Use of Markers, CMU News, 2014
Motion capture apparatus and method (Patent No.: US 8805024 B2)
Hanbyul Joo, Seong-Jae Lim, Ji-Hyung Lee, Bon-Ki Koo
Method for automatic rigging and shape surface transfer of 3D standard mesh model based on muscle and nurbs by using parametric control (Patent No.: US 7171060 B2)
Seong Jae Lim, Ho Won Kim, Hanbyul Joo, Bon Ki Koo
3D model shape transformation method and apparatus (Patent Application No.: US 20120162217 A1)
Seong-Jae Lim, Hanbyul Joo, Seung-Uk Yoon, Ji-Hyung Lee, Bon-Ki Koo.