My Name is Ruizhe Wang, and I am a Computer Vision researcher

In 2012, I joined the Computer Vision Lab at the University of Southern California and now I am working under the guidance of Prof. Gerard Medioni. Before that, I obtained my MS degree from CalTech in 2012 and BS degree from Tsinghua University in 2010.

My interest is focused on using the commodity 3D sensors, e.g., Kinect, to provide fast, cheap and reliable solutions to various problems. On the 3D scanning project, we developed a contour-coherence based registration algorithm that allows complete and accurate reconstruct of rigid as well as articulated objects from as few as 4 range scans. On top of that, we built an accurate and practical 3D whole body scanner using a single Kinect device. On the Point of Care Monitoring (POCM) project, we are building a non-invasive monitoring system for patients with Parkinson's Disease.


3D Scanning

We develop a contour-coherence based registration algorithm to align wide baseline range scans. The traditional registration algorithms, e.g., ICP, fail in this case, as many closest point-to-point corresponding pairs are incorrect in presense of limited overlap. The contour-coherence, on the other hand, still serves as a strong clue, as no matter the amount of overlap only the 2D contour points are used for registration. An example is given when registering two range scans of the stanford bunny with an overlap of approximately 40% (top left figure). The ICP style algorithms fail as most correspondences are incorrect. On the other hand, we successfully register these two range scans using contour-coherence (top right figure).

We apply contour-coherence to address the problem of multi-view rigid registration, and further extend it to solve the problem of multi-view piece-wise rigid registration. This allows us to reconstruct rigid as well as articulated objects from as few as 4 range scans, i.e., front, back, and two profiles.

On top of this, we build a 3D Body Scanner, using a low-cost Kinect device, to accurately capture the 3D shape of human bodies. Our scanning system robustly provides globally accurate results with preserved small details. The complete system is easy to set-up (i.e., put the Kinect on table or tripod) and the instructions are easy to follow (i.e., turn when asked). In less than 2 minutes, including the data acquisition, an accuate and complete model is generated.

Point of Care Monitoring (POCM)

For patients with Parkinson's Disease, the current patient-clinician evaluation mode is very ineffective (top left figure). As such, we propose a reliable and accurate home monitoring and evaluation system as an attractive alternative (top right figure). While traditional home monitoring systems heavily rely on the use of invasive sensors, e.g., accelerometer and gyroscrope, we offer a solution using a single non-invasive 3D sensor. The subject is asked to perform standardized medical tests in front of the 3D sensor, while the depth sensor monitors his/her motion by producing a skeletal stream. We propose a Temporal Alignment and Spatial Summarization (TASS) algorithm to process this noisy high-dimensional periodic time-series data, and produce a denoised skeletal sequence which captures the subject's most consistent motion pattern. Important biomedical indicators are further extracted from this robust representation.



  1. Ruizhe Wang, Jongmoo Choi and Gerard Medioni, "3D Modeling from Wide Baseline Range Scans using Contour Coherence", Proc. of the 25th IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2014), Columbus, Ohio, June 2014 new!
    [PDF](coming soon) [Video] [Code](expected May 2014)
  2. Ari Shapiro, Andrew Feng, Ruizhe Wang, Hao Li, Mark Bolas, Gerard Medioni and Evan Suma, "Rapid Avatar Capture and Simulation using Commodity Depth Sensors", Proc. of the 27th Conference on Computer Animation and Social Agents (CASA 2014), Houston, Texas, May, 2014 new!
    [PDF](coming soon) [Video]
  3. Ruizhe Wang, Matthias Hernandez, Jongmoo Choi and Gerard Medioni, "Accurate 3D Face and Body Modeling from a Single Fixed Kinect", Proc. of the 4th International Conference on 3D Body Scanning Technologies (3DBST 2013), Long Beach, California, Nov, 2013
    [PDF] [Slides]
  4. Ruizhe Wang, Gerard Medioni, Carolee J Winstein and Cesar Blanco, "Home Monitoring Musculo-skeletal Disorders with a Single 3D Sensor", International Workshop on Human Activity Understanding from 3D Data in conjunction with 23th IEEE Conference on Computer Vision and Pattern Recognition (CVPRW 2013), Portland, Oregon, June 2013
    [PDF] [Video] [Poster] [Slides] [Code](expected Apr 2014)
  5. Ruizhe Wang, Jongmoo Choi and Gerard Medioni, "Accurate Full Body Scanning from a Single Fixed 3D Camera", Proc. of the 2nd International Conference on 3D Imaging, Modeling, Processing, Visualization and Transmission (3DimPVT 2012), ETH Zurich, Switzerland, Oct 2012
    [PDF] [Video] [Poster] [Slides]


  1. Ari Shapiro, Andrew Feng, Ruizhe Wang, Gerard Medioni, Mark Bolas and Evan A. Suma, "Automatic Acquisition and Animation of Virtual Avatars" Proc. of the 21st IEEE International Conference on Virtual Reality (VR 2014), Minneapolis, Minnesota, Mar~Apr, 2014 new!
  2. Farnoush B Kashani, Gerard Medioni, Khanh Nguyen, Luciano Nocera, Cyrus Shahabi, Ruizhe Wang, Cesar E Blanco, Yi-An Chen, Yu-Chen Chung, Beth Fisher, Sara Mulroy, Philip Requejo and Carolee J Winstein "Monitoring mobility disorders at home using 3D visual sensors and mobile sensors", Proc. of the 4th Conference on Wireless Health (WH 2013), Johns Hopkins University, Baltimore, Maryland, Nov 2013


  1. Gerard Medioni, Jongmoo Choi and Ruizhe Wang, "3D Body Modeling from One or More Depth Cameras in the Presence of Articulated Motion" US Patent App. 13/801,099, 2013


Email: ruizhewa@usc.edu or ruizhewa@gmail.com
Phone: 1-(626)3908301
Office: 3737 Watt Way, PHE 101, University of Southern California, Los Angeles, CA, 90089

Free Web Counter
Since 3/27/2014