Kong Man (German) Cheung

Postdoctoral Fellow, Robotics Institute, Carnegie Mellon University

Current Collaboration: Jessica Hodgins, Takeo Kanade and Simon Baker
Current Laboratories: Asimo Lab., Virtualized Reality Lab., Vision Lab., Graphics Lab.
Research Interests: 3D computer vision/graphics
Thesis Advisors: Takeo Kanade and Simon Baker

Contact Information:

Address: Robotics Institute
Labs: Vision Lab., Smith Hall 101
Carnegie Mellon University
Virtualized Reality Lab., Newell Simon Hall Level B
5000 Forbes Avenue
Phone: 412-268-3127 (Vision Lab.)
Pittsburgh PA 15213
412-268-6542 (Virtualized Reality Lab.)
Email: german@ux2.sp.cs.cmu.edu
Fax: 412-268-5571

Resume: txt, pdf.

Research

My research focuses on computer vision/graphics, especially in the area of 3D shape reconstruction from multiple cameras. I am interested in applying computer vision for graphics applications. Recently I have extended the shape reconstruction method called Shape-From-Silhouette to across time and applied the theory to the applications of human kinematic modeling, markerless motion capture and motion transfer (please see the project pages below for details). Other areas that interest me include projective geometry, human related problems such as face recognition and behavior understanding, structure from motion, projective geometry, camera calibration, image-based rendering, etc. I am also involved in the CMU Virtualized Reality Project and maintain the associated CMU 3D Room.

Projects

Current Projects

Past Projects

Real-time 3D Reconstruction/Fitting of Human Voxel Models

Temporal Shape-From-Silhouette

3D Human Kinematic Modeling and Markerless Motion Capture

Human Motion Transfer

3D Video Reconstruction of Skeletal Anatomy

Interactive Multi-Grid Image Warping

For my research, I wrote a lot of GUIs involving 2D/3D images and objects. The following are two example screenshots of two different examples (click on the picture to magnify) of GUI I wrote using FLTK.

Publications

Recent Publications

Older Publications