Nonrigid stereo reconstruction using linear programming
Pages 63 - 68
Abstract
Nonrigid reconstruction plays an important role in many applications like image-based modeling, human-computer interaction. In this paper, we propose an effective approach for 3D non-rigid structure reconstruction using linear programming from an image pair taken with a stereo rig. In contrast to previous approaches, the proposed method neither involves smoothness constraints nor need prior knowledge between consecutive frames, which enables us to recover shapes of surfaces with smooth, sharp and other complex deformations from a single image pair. Specifically, we model the surface as a triangulated mesh and formulate the reconstruction problem as a Linear Programming (LP) problem using L∞ that can be effectively solved. The LP problem consists of data constraints which are 3D-to-2D keypoint correspondences and shape constraints which preserve original lengths of mesh edges. The robustness and accuracy of our approach are evaluated quantitatively on synthetic data and on real data.
References
[1]
. B. Ashraf and S. Lucey and J. F. Cohn and T. Chen and Z. Ambadar and K. M. Prkachin. The painful face - Pain expression recognition using active appearance models. Image and Vision Computing, 2009.
[2]
. S. Bhat and C. D. Twigg and J. K. Hodgins and P. K. Khosla and Z. Popovic and S. M. Seitz. Estimating cloth simulation parameters from video, 2003.
[3]
. Brand. A direct method for 3d factorization of nonrigid motion observed in 2d. CVPR, 2005.
[4]
. F. Cootes and G. J. Edwards and C. J. Taylor. Active appearance models. PAMI, 2001.
[5]
Martin A. Fischler and Robert C. Bolles. Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography. Communications of the ACM, 1981.
[6]
. Hartley and P. Sturm. Triangulation. Computer Vision and Image Understanding, 1997.
[7]
. Hartley and A. Zisserman. Multiple View Geometry in Computer Vision. Cambridge University Press, 2004.
[8]
. Kahl. Multiple View Geometry and the L∞ norm. ICCV, 2005.
[9]
. Ke and T. Kanade. Quasiconvex Optimization for Robust Geometric Reconstruction. ICCV, 2005.
[10]
. Lowe. Distinctive image features from scale-invariant keypoints. IJCV, 2004.
[11]
. Matthews and S. Baker. Active appearance models revisited. IJCV., 2004.
[12]
. Metaxas and D. Terzopoulos. Constrained deformable superquadrics and nonrigid motion tracking. PAMI, 1993.
[13]
. Perriollat and R. Hartley and A. Bartoli. Twin Gaussian Process for Structured Prediction. BMVC, 2008.
[14]
. Salzmann and R. Hartley and P. Fua. Convex Optimization for Deformable Surface 3-D Tracking. ICCV, 2007.
[15]
. Seo and R. Hartley. A Fast Method to Minimize L∞ Error Norm for Geometric Vision Problems. ICCV, 2007.
[16]
. Shen and Y. Liu and W. Lu. Monocular 3D tracking of deformable surfaces using sequential second order cone programming. PR, 2010.
[17]
. Sim and R. Hartley. Removing Outliers Using The L∞ Norm. CVPR, 2006.
[18]
. Sturm. Using sedumi 1.02, a matlab toolbox for optimization over symmetric cones. Optimization Methods and Software, 2010.
[19]
. Torresani and A. Hertzmann and C. Bregler. Non-Rigid Structure-From-Motion: Estimating Shape and Motion with Hierarchical Priors. PAMI, 2008.
[20]
. Xiao and T. Kanade. Uncalibrated perspective reconstruction of deformable structures. ICCV, 2005.
[21]
. Zhu and S. Hoi and Z. Xu and M. Lyu. An Effective Approach to 3D Deformable Surface Tracking. ECCV, 2008.
Index Terms
- Nonrigid stereo reconstruction using linear programming
Recommendations
Convex optimization for nonrigid stereo reconstruction
We present a method for recovering 3-D nonrigid structure from an image pair taken with a stereo rig. More specifically, we dedicate to recover shapes of nearly inextensible deformable surfaces. In our approach, we represent the surface as a 3-D ...
Stereo Reconstruction from Multiperspective Panoramas
Abstract--A new approach to computing a panoramic (360 degrees) depth map is presented in this paper. Our approach uses a large collection of images taken by a camera whose motion has been constrained to planar concentric circles. We resample regular ...
Depth from Defocus vs. Stereo: How Different Really Are They?
Special issue on computer vision research at the TechnionDepth from Focus (DFF) and Depth from Defocus (DFD) methods are theoretically unified with the geometric triangulation principle. Fundamentally, the depth sensitivities of DFF and DFD are not different than those of stereo (or motion) based systems ...
Comments
Information & Contributors
Information
Published In
October 2010
78 pages
Copyright © 2010 ACM.
Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected]
Sponsors
Publisher
Association for Computing Machinery
New York, NY, United States
Publication History
Published: 29 October 2010
Check for updates
Author Tags
Qualifiers
- Research-article
Conference
MM '10
Sponsor:
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 155Total Downloads
- Downloads (Last 12 months)1
- Downloads (Last 6 weeks)0
Reflects downloads up to 25 Feb 2025
Other Metrics
Citations
View Options
Login options
Check if you have access through your login credentials or your institution to get full access on this article.
Sign in