QIAN-YI ZHOU - Stanford University

Q IAN -Y I Z HOU
Postdoctoral Researcher
Computer Science, Stanford University
353 Serra Mall, Gates 396
Stanford, CA 94305
Tel: 323-893-9083
[email protected]
http://www.stanford.edu/~qianyizh/
Last updated: February, 2014
Objective
• A tenure-track faculty position in the Computer Science department of a leading university,
or a research position at a top research laboratory.
Research Interests
• I am broadly interested in computer vision and computer graphics. In particular, I tackle
the challenges in large scale 3D reconstruction from massive amount of 3D data made
available by commodity range cameras and commercial grade laser scanners. The ultimate
goal of my research is to make computers understand the 3D reality of the real world from
big visual data. My current research areas include but not limited to the followings.
–
–
–
–
–
Large scene reconstruction with commodity range cameras
Urban modeling from point clouds
Pattern recognition in geometry and imagery
Analyzing, repairing and editing the topology of 3D models
Scalable computing framework for large scale 3D data
Current Position
• Postdoctoral Researcher
September 2012 to present
– Computer graphics lab, Stanford University
– Advisor: Vladlen Koltun
Education
• Ph.D. in Computer Science - University of Southern California, CA
August 2012
– Thesis: 3D Urban Modeling from City-scale Aerial LiDAR Data
– Advisor: Ulrich Neumann
• M.S. in Computer Science - Tsinghua University, Beijing
June 2007
– Thesis: OcTree Based Topology Repair and Editing
– Advisor: Shi-Min Hu
– Graduated with honors
• B.E. in Computer Science - Tsinghua University, Beijing
June 2005
– Graduated with honors
Publications
• Qian-Yi Zhou and Vladlen Koltun, “Simultaneous Localization and Calibration”, CVPR
2014
1
• Qian-Yi Zhou, Stephen Miller and Vladlen Koltun, “Elastic Fragments for Dense Scene
Reconstruction”, ICCV 2013 (oral presentation, acceptance rate: 2.5%)
• Qian-Yi Zhou and Vladlen Koltun, “Dense Scene Reconstruction with Points of Interest”,
ACM SIGGRAPH 2013
• Qian-Yi Zhou and Ulrich Neumann, “2.5D Building Modeling by Discovering Global
Regularities”, IEEE CVPR 2012
• Qian-Yi Zhou and Ulrich Neumann, “Complete Residential Urban Area Reconstruction
from Dense Aerial LiDAR Point Clouds”, Graphical Models 2012
• Qian-Yi Zhou and Ulrich Neumann, “Modeling Residential Urban Areas from Dense
Aerial LiDAR Point Clouds”, Computational Visual Media Conference 2012
• Na Chen, Qian-Yi Zhou and Viktor Prasanna, “Understanding Web Images by Object
Relation Network”, WWW 2012
• Qian-Yi Zhou and Ulrich Neumann, “2.5D Building Modeling with Topology Control”,
IEEE CVPR 2011
• Qian-Yi Zhou and Ulrich Neumann, “2.5D Dual Contouring: A Robust Approach to
Creating Building Models from Aerial LiDAR Point Clouds”, ECCV 2010 (oral
presentation, acceptance rate: 3.3%)
• Qian-Yi Zhou and Ulrich Neumann, “A Streaming Framework for Seamless Building
Reconstruction from Large-Scale Aerial LiDAR Data”, IEEE CVPR 2009
• Qian-Yi Zhou and Ulrich Neumann, “Fast and Extensible Building Modeling from
Airborne LiDAR Data”, ACM GIS 2008
• Tao Ju, Qian-Yi Zhou, Michiel van de Panne, Daniel Cohen-Or and Ulrich Neumann,
“Reusable Skinning Templates Using Cage-based Deformations”, ACM SIGGRAPH ASIA
2008
• Junho Kim, Miao Jin, Qian-Yi Zhou, Feng Luo, and and Xianfeng Gu, “Computing
Fundamental Group of General 3-Manifold”, International Symposium on Visual Computing
2008
• Tao Ju, Qian-Yi Zhou and Shi-Min Hu, “Editing The Topology of 3D Models by Sketching”,
ACM SIGGRAPH 2007
• Qian-Yi Zhou, Tao Ju, and Shi-Min Hu, “Topology Repair of Solid Models Using
Skeletons”, IEEE Trans. Vis. Comput. Graph. 2007
• Yu-Kun Lai, Qian-Yi Zhou, Shi-Min Hu, Johannes Wallner and Helmut Pottmann, “Robust
Feature Classification and Editing”, IEEE Trans. Vis. Comput. Graph. 2007
• Yong-Jin Liu, Qian-Yi Zhou and Shi-Min Hu, “Handling Degenerate Cases in Exact
Geodesic Computation on Triangle Meshes”, Computer Graphics International, 2007
• Yu-Kun Lai, Qian-Yi Zhou, Shi-Min Hu and Ralph R. Martin, “Feature Sensitive Mesh
Segmentation”, ACM Symp. Solid and Physical Modeling 2006
Systems and Software
• Dense Scene Reconstruction - to be announced in 2013
2
– An automatic system to reconstruct detailed scene geometry from range videos produced
by commodity handheld cameras. The implementation is based on my ICCV 2013 paper “Elastic Fragments for Dense Scene Reconstruction” and my SIGGRAPH 2013 paper
“Dense Scene Reconstruction with Points of Interest”.
– The dataset used in these two papers is also freely available online (Google: “3d scene
dataset”).
• Automatic Urban Modeling System - 2007 to 2012
– A fully automatic urban modeling system which creates 3D polygonal models from aerial
point cloud (LiDAR). This system contains full functionality from processing the raw
point clouds, to generating a complete set of urban models including buildings, trees, and
ground. This system is capable of seamlessly handling city-scale data sets with billions
of points as input.
– Companies and organizations which have used or tested this system include: Airborne 1
Corp., Sanborn, Chevron, The Johns Hopkins University Applied Physics Laboratory.
• 2.5D Dual Contouring - 2010
– A robust, efficient method to creating 2.5D building models from aerial LiDAR point
clouds. It is the implementation of my ECCV 2010 paper “2.5D Dual Contouring: A
Robust Approach to Creating Building Models from Aerial LiDAR Point Clouds”. Freely
available (Google: “2.5D Dual Contouring”)..
• MendIt - 2007
– MendIT is a topology editing software for 3D models with user interactions. The algorithm of this software is based on my SIGGRAPH 2007 paper “Editing The Topology of
3D Models by Sketching”. Freely available on my homepage.
• TopoMender - 2006
– TopoMender is a fully automatic topology noise removal software, based on my TVCG
2007 paper “Topology Repair of Solid Models Using Skeletons”. Freely available (Google:
“TopoMender”).
– Companies and organizations which have used or tested this system include: Pacific
Northwest National Laboratory, UCLA Laboratory of Neuro-Imaging, and many other
research groups in top universities.
Advising and Teaching
• Tao Du, master student, Stanford, September 2013 to present
• Sungjoon Choi, PhD student, Stanford, May 2013 to present
• Jing Liu, exchange PhD student, Stanford, October 2012 to December 2012
• Rongqi Qiu, PhD student, USC, August 2011 to May 2012
• Rongqi Qiu, undergraduate student summer intern, USC, July 2010 to August 2010
• CS 580, 3D Graphics and Rendering, guest lecturer, USC, Fall 2008
Presentation and Invited Talks
• February 24, 2014 - “Large Scale 3D Reconstruction”, University of Utah, Salt Lake City, UT
• February 5, 2014 - “Large Scale 3D Reconstruction”, Google, Mountain View, CA
3
• October 18, 2013 - “Dense Scene Reconstruction”, Microsoft, Sunnyvale, CA
• July 24, 2013 - “Dense Scene Reconstruction with Points of Interest”, ACM SIGGRAPH
2013, Anaheim, CA
• June 18, 2012 - “2.5D Building Modeling by Discovering Global Regularities”, IEEE CVPR
2012, Providence, RI
• March 21, 2012 - “2.5D Urban Modeling from Aerial Point Clouds”, Nokia Research, Palo
Alto, CA
• March 8, 2012 - “2.5D Building Modeling by Discovering Global Regularities”, USC CS
department annual research review 2012, Los Angeles, CA
• December 8, 2011 - “2.5D Building Modeling”, Graphics Lab, Tsinghua University, Beijing,
China
• July 13, 2011 - “System Demo: Automatic Urban Modeling from Aerial LiDAR”, Airborne 1
Corp, El Segundo, CO
• June 23, 2011 - “2.5D Building Modeling with Topology Control”, IEEE CVPR 2011,
Colorado Springs, CO
• March 25, 2011 - “2.5D Dual Contouring for Building Reconstruction”, USC CS department
annual research review 2011, Los Angeles, CA
• December 14, 2010 - “Automatic Urban Modeling from Aerial LiDAR”, Graphics Lab,
Tsinghua University, Beijing, China
• September 9, 2010 - “2.5D Dual Contouring: A Robust Approach to Creating Building
Models from Aerial LiDAR Point Clouds”, ECCV 2010, Hersonissos, Heraklion, Crete,
Greece
• March 23, 2010 - “City-scale Urban Reconstruction from Aerial LiDAR Data”, USC CS
department annual research review 2010 (award winner), Los Angeles, CA
• June 25, 2009 - “A Streaming Framework for Seamless Building Reconstruction from
Large-Scale Aerial LiDAR Data”, IEEE CVPR 2009, Miami Beach, FL
• February 11, 2009 - “TopoMender: OcTree Based Topology Repair and Editing”, UCLA
Laboratory of Neuro-Imaging, Los Angeles, CA
• November 11, 2008 - “Fast and Extensible Building Modeling from Airborne LiDAR Data”,
CS 580 course (3D Graphics and Rendering), USC, Los Angeles, CA
• November 5, 2008 - “Fast and Extensible Building Modeling from Airborne LiDAR Data”,
ACM GIS 2008, Irvine, CA
• August 5, 2007 - “Editing The Topology of 3D Models by Sketching”, ACM SIGGRAPH
2007 fast forward, San Diego, CA
Professional Service
• Journal Reviewer
–
–
–
–
Graphical Models
IEEE Transaction on Visualization and Computer Graphics
Computer Aided Design
Computer Aided Geometric Design
4
– Remote Sensing
– IEEE Transactions on Automation Science and Engineering
– Journal of Computer Science and Technology
• Conference Reviewer
–
–
–
–
–
–
–
SIGGRAPH Asia
International Conference on Pattern Recognition (ICPR)
Computational Visual Media Conference
Pacific Graphics
Asian Conference on Computer Vision (ACCV)
ACM Solid and Physical Modeling Symposium (ACM SPM)
ECCV 2010 Workshop on Reconstruction and Modeling of Large-Scale 3D Virtual Environments
Selected Awards
• 2007 to 2011 - Provost’s Ph.D. Fellowship from University of Southern California
• March 2010 - Winner of “best poster for technical strength” in 2010 annual research review
of Computer Science, University of Southern California
• 2007 - Outstanding M.S. thesis, Computer Science, Tsinghua University, Beijing
• 2005 - Outstanding B.E. thesis, Computer Science, Tsinghua University, Beijing
• 2005 - Outstanding Graduate of the Beijing city
5

Download Report