Publications

Publications

Referred papers:

"Handling Uncertainties in Geometric Reconstruction Using Quasiconvex Optimization",
Qifa Ke and Takeo Kanade,
IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2006), to appear, New York City, June 2006.

"Quasiconvex Optimization for Robust Geometric Reconstruction",
Qifa Ke and Takeo Kanade,
Tenth IEEE International Conference on Computer Vision (ICCV 2005), Beijing, China, October 2005
(oral presentation, acceptance ratio < 4%)

“Robust L₁ Norm Factorization in the Presence of Outliers and Missing Data by Alternative Convex Programming”,
Qifa Ke and Takeo Kanade,
IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2005), vol. 1, pp. 739-746, June 2005.
(part of the content also appeared in tech. report CMU-CS-03-172)

“Real-Time and 3D Vision for Autonomous Small and Micro Air Vehicles”,
Takeo Kanade, Omead Amidi, and Qifa Ke,
invited paper, IEEE Conf. on Decision and Control (CDC 2004), pp. 1655-1662, Dec. 2004.

“Robust Subspace Clustering by Combined Use of kNND Metric and SVD Algorithm”,
Qifa Ke and Takeo Kanade,
IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2004), vol. 2, pp. 592-599, June 2004.

“Transforming Camera Geometry to A Virtual Downward-Looking Camera: Robust Ego-Motion Estimation and Ground-Layer Detection”,
Qifa Ke and Takeo Kanade,
IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2003), vol. 1, pp. 390-397, June 2003.

“A Robust Subspace Approach to Layer Extraction”,
Qifa Ke and Takeo Kanade,
IEEE Workshop on Motion and Video Computing (Motion 2002), pp. 37-43, December 2002.
Lockheed-Martin Best Paper Award

“A Subspace Approach to Layer Extraction”,
Qifa Ke and Takeo Kanade,
IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2001), vol. 1, pp. 255-262, December 2001.
(oral presentation, acceptance ratio < 8%)

“Emulation of Multi-Hop Wireless Ad Hoc Networks”,
Qifa Ke, D. Maltz, and D. B. Johnson,
Seventh International Workshop on Mobile Multimedia Communications (MoMuC 2000), October 2000.

“Efficient Bundle Adjustment with Virtual Key Frames: A Hierarchical Approach to Multi-Frame Structure from Motion”,
Heung-Yeung Shum, Qifa Ke, and Zhengyou Zhang,
IEEE Conference on Computer Vision and Pattern Recognition (CVPR 1999), vol. 2, pp. 538-543, June 1999.

“Recovering Epipolar Geometry by Reactive Tabu Search”,
Qifa Ke, Gang Xu, and Songde Ma,
Sixth IEEE International Conference on Computer Vision (ICCV 1998), pp. 767-771, January 1998.

“The Design and Application of Multi-Scale Differential Filters”,
Qifa Ke, Lixin Wang, and Songde Ma,
Chinese Journal of Computers, Vol. 21(3), pp.234-244, 1998

“Curvatures in Scale Space for Corner Enhancement”,
Ge Cong, Qifa Ke, and Songde Ma,
Chinese Journal of Computers, Vol. 21(4), 1998.

“A Tabu Search Method for Geometric Primitive Extraction”,
Q. Ke, T. Jiang, and S. Ma,
Pattern Recognition Letters, Vol.18(14), pp.1443-1452, December 1997.

“Energy-Based Method for Road Extraction from Satellite Images”,
Qifa Ke, Jing Xiao, Zhiyong Yang, and Songde Ma,
IAPR Workshop on Machine Vision and Applications (MVA 1996), Tokyo, Japan, 1996.

“Differentiation Filter Design: Theories and Applications”,
Qifa Ke and Songde Ma,
The 4^th International Conference on Control, Automation, Robotics and Vision (ICARCV 1996), Singapore, 1996.
(Finalist for the Best Paper Award)

Technical reports:

"Quasiconvex Optimization for Robust Geometric Reconstruction",
Qifa Ke and Takeo Kanade,
Tech. Report CMU-RI-TR-05-57, Robotics Institute, Carnegie Mellon University, November 2005.
Submitted to IEEE PAMI (updated version of tech. report).
Conference version appeared in ICCV 2005.

“Textureless Layers”,
Qifa Ke, Simon Baker, and Takeo Kanade,
Tech. Report CMU-RI-TR-04-17, Robotics Institute, Carnegie Mellon University, March 2004.
Example results.

“A Robust Subspace Approach to Extracting Layers from Image Sequences”,
Qifa Ke,
Doctoral Thesis, Tech. Report CMU-CS-03-173, Computer Science Department, Carnegie Mellon University, August 2003.

“Robust Subspace Computation Using L₁ Norm”,
Qifa Ke and Takeo Kanade,
Tech. Report CMU-CS-03-172, Computer Science Department, Carnegie Mellon University, 2003.

“A Subspace Approach to Layer Extraction and Its Application to Patch-Based Structure from Motion and Video Compression”,
Qifa Ke and Takeo Kanade,
Tech. Report CMU-CS-01-168, Computer Science Department, Carnegie Mellon University, 2001.

“Multi-Scale Differential Filters: Theory, Design, and Applications”,
Qifa Ke,
Master Thesis, Tech. Report, National Lab. of Pattern Recognition and Artificial Intelligence, Chinese Academy of Sciences, 1997.

“A Gateway Connecting LAN with PSTN for Sharing Facsimile”,
Qifa Ke,
Bachelor Thesis, Tech. Report, Dept. of Electronic Engineering, Univ. of Sci. & Tech. of China, 1994.

Patent:

“Rendering with ConCentric Mosaics”,
Heung-Yeung Shum, Li-Wei He, and Qifa Ke,
-- International patent number: WO 00/68890, granted November 2000;
-- US patent number: 6750860, granted June 2004.

[ back to homepage ]