Important Dates

Camera Ready: March 18, 2011

Early Registration: April 15 2011

Conference: May 16-19, 2011




General Chairs

Guy Godin (NRC, Canada)
Hongbin Zha (Peking University, China)

Program Chairs

Michael Goesele (TU Darmstadt, Germany)
Yasuyuki Matsushita (MSR-Asia, China)
Ryusuke Sagawa (AIST, Japan)
Ruigang Yang (University of Kentucky, USA)

Panel/Challenge Chair

Ioannis Stamos (City University of New York, USA)

Demonstration Chair

Huimin Yu (Zhejiang University, China)

Local Arrangement Chairs

Jian Wan (Hangzhou Dianzi University, China)
Mingmin Zhang (Zhejiang University, China)

Publication Chair

Chang Shu (NRC, Canada)

Finance Chair

Zhigeng Pan (Zhejiang University, China)

Publicity Chairs

Xin Chen (NAVTEQ, USA)
Qili Zhou (Hangzhou Dianzi University, China)

Web Chair

Xinyu Huang (North Carolina Central University, USA)

3DIMPVT 2011: The First Joint 3DIM/3DPVT Conference
3D Imaging • Modeling • Processing • Visualization • Transmission
Hangzhou, China, May 16-19, 2011

Printable PDF of CfP

In cooperation with Eurographics    Eurographics



Note that the original tutorial by Gary Bradski, titled "OpenCV, PCL, and Kinect" is cancelled due to some family emergency of the speaker. Attendees with tutorial only registration can request for a full refund by sending an email to

Recent Active 3D Scanning System and Techniques
Hiroshi Kawasaki and Ryusuke Sagawa

Recently, various kind of 3D scanning system are now widely available. For example, Kinect is one of the most successful device which can capture wide area with 30fps with inexpensive price. Vivid is another system which can capture the shape with 50-100 micron precision. Although those devices can retrieve depth information of the scene, accuracy, resolution and frame rate are significantly different each other. Indeed, 3D reconstruction algorithm for each device is totally different. In this tutorial, we introduce basic algorithm of current 3D scanning devices as well as practical implementation for each device.


Hiroshi Kawasaki

Hiroshi Kawasaki is a professor of Department of Information and Biomedical Engineering Faculty of Engineering, Kagoshima University, Japan. He received his ME and Ph.D. degree from University of Tokyo, Japan, in 2000 and 2003, respectively. He started working at Kagoshima University, Japan, in 2010. Prior to Kagoshima University, He worked at Saitama University from 2003. He also worked at Microsoft Research Redmond, WA, USA in 2000 and also worked at INRIA Rhone-alpes, France, as a visiting professor in 2009. His current research interests are in 3D capture of moving objects and real-time rendering of it. Applications for VR/MR systems and ITS are also his important research topic. He has published over 80 research papers including ICCV, CVPR, IJCV, 3DIM and Eurographics in computer vision and computer graphics. He also won several awards including Songde Ma Outstanding Paper Award (best paper of ACCV) in 2007 and best paper of PSIVT held in Singapore in 2010. You can check more detail at the following site:

Ryusuke Sagawa

Ryusuke Sagawa is a researcher of Intelligent Systems Research Institute, National Institute of Advanced Industrial Science and Technology, Tsukuba, Japan, from 2010. He received a BE in Information Science from Kyoto University, Japan, in 1998. He received a ME in Information Engineering in 2000 and Ph.D. in Information and Communication Engineering from the University of Tokyo, Japan in 2003. He was an assistant professor from 2003 to 2010 at the Institute of Scientific and Industrial Research, Osaka University, Japan. He also worked at ETH Zurich, Switzerland in 2008 as a visiting researcher. His primary research interests are computer vision, computer graphics and robotics (mainly geometrical modeling and visualization).


Geometric Modeling and Processing
Ligang Liu

Thanks to the recent innovation in 3D acquisition technology, such as 3D laser scanning, computational photography, computer tomography, magnetic resonance imaging, and radar, which enables highly accurate digitization of complex 3D objects, computer graphics and computer vision are increasingly merging into the discipline of geometry processing during the last two decades. It is concerned with mathematical models and algorithms for analyzing and manipulating geometric data. Numerous scientific disciplines rely on the analysis and processing of such geometric data to understand intricate geometric structures and facilitate new scientific discoveries.
This tutorial investigates the substantially important role that geometric modeling and processing plays in 3D graphics and vision as well as the digital manufacturing technology. The tutorial demonstrates various operations in geometry processing, particularly in shape modeling and reconstruction from point samples, which include geometric registration and matching, filtering operations for noise removal, shape repairing, and interactive editing and deformation etc. Some demos are also shown in the tutorial to illustrate how user interaction enhances the modeling and processing of geometric shapes.


Ligang Liu is a professor of mathematics and computer graphics at Zhejiang University, China. He studied geometric modeling and computer graphics at Zhejiang University, where he received his Ph.D. degree in 2001. Between 2001 and 2004, he worked at Microsoft Research Asia and in 2004, he moved to Zhejiang University. He paid an academic visit at Harvard University during 2009 and 2010. His research interests include geometric modeling and processing, computer graphics, and image processing. He has published a number of papers in these areas and has authored 5 SIGGRAPH (Asia) papers and 4 Eurographics papers. Some of his works could be found at his research website:

Tutorial syllabus (tentative) (3 hours with a 30-minute coffee break)

1. Introduction (5 minutes)

2. Surface representation (15 minutes)

3. Data acquisition (15 minutes)

4. Geometric registration (30 minutes)

Coffee break (30 minutes)

5. Shape reconstruction and modeling (30 minutes)

6. Shape smoothing and repair (20 minutes)

7. Shape editing and deformation (30 minutes)

8. Wrap-up (5 minutes)