A Comparison Study of Five 3 D Modeling Systems Based on the SfM Principles ∗

We present a comparison study of five 3D modeling systems base d on the structure-from-motion principles (Bundler, Bundler+PMVS2, Project Photofly from Autodesk, ARC 3D Web Service, and our own). To ensure that the comparison is fair, we have included only those 3D modeling systems that are available for use on the Web or locally in a binary format, and comprise a complete, fully-automated 3D pipeline that leads from input images to 3D models, withou any user intervention, and without datadependent parameter tuning. In addition to ground-truthed 3D ata, we have used a testbed comprising over 100 data sets, with over three thousand images, represe nting a variety of 3D scenes, collected from a large number of consumer-market digital cameras and camer a phones of many makes/models, and all without prior camera calibration, use of special equipm ent (tripod, lens, etc.) and lighting (laser and structured light projection), and user training in imag e cquisition. In the paper, we introduce the methodology of the comparison, justify the crucial choices made in the study, present the results, and provide an analysis of these results.

[1]  John E. Dennis,et al.  Numerical methods for unconstrained optimization and nonlinear equations , 1983, Prentice Hall series in computational mathematics.

[2]  Yoshiaki Shirai,et al.  Three-Dimensional Computer Vision , 1987, Symbolic Computation.

[3]  Gang Xu,et al.  Epipolar Geometry in Stereo, Motion and Object Recognition , 1996, Computational Imaging and Vision.

[4]  Richard I. Hartley,et al.  In Defense of the Eight-Point Algorithm , 1997, IEEE Trans. Pattern Anal. Mach. Intell..

[5]  Steven H. Schwartz,et al.  Visual Perception: A Clinical Orientation , 1998 .

[6]  Bernhard P. Wrobel,et al.  Multiple View Geometry in Computer Vision , 2001 .

[7]  Shigeo Abe DrEng.  Pattern Classification , 2001, Springer London.

[8]  D. Scharstein,et al.  A Taxonomy and Evaluation of Dense Two-Frame Stereo Correspondence Algorithms , 2001, Proceedings IEEE Workshop on Stereo and Multi-Baseline Vision (SMBV 2001).

[9]  Eric R. Ziegel,et al.  The Elements of Statistical Learning , 2003, Technometrics.

[10]  Leif Kobbelt,et al.  A survey of point-based techniques in computer graphics , 2004, Comput. Graph..

[11]  G LoweDavid,et al.  Distinctive Image Features from Scale-Invariant Keypoints , 2004 .

[12]  Reinhard Koch,et al.  Visual Modeling with a Hand-Held Camera , 2004, International Journal of Computer Vision.

[13]  Long Quan,et al.  A quasi-dense approach to surface reconstruction from uncalibrated images , 2005, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[14]  Tom Drummond,et al.  Fusing points and lines for high performance tracking , 2005, Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1.

[15]  Richard Szeliski,et al.  A Comparison and Evaluation of Multi-View Stereo Reconstruction Algorithms , 2006, 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06).

[16]  Steven M. Seitz,et al.  Photo tourism: exploring photo collections in 3D , 2006, ACM Trans. Graph..

[17]  Olivier Stasse,et al.  MonoSLAM: Real-Time Single Camera SLAM , 2007, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[18]  G. Klein,et al.  Parallel Tracking and Mapping for Small AR Workspaces , 2007, 2007 6th IEEE and ACM International Symposium on Mixed and Augmented Reality.

[19]  Richard Szeliski,et al.  Modeling the World from Internet Photo Collections , 2008, International Journal of Computer Vision.

[20]  Jan-Michael Frahm,et al.  Detailed Real-Time Urban 3D Reconstruction from Video , 2007, International Journal of Computer Vision.

[21]  Yuan-Fang Wang,et al.  Toward automated model building from video in computer-assisted diagnoses in colonoscopy , 2007, SPIE Medical Imaging.

[22]  J. Ponce,et al.  Accurate, Dense, and Robust Multi-View Stereopsis , 2007, 2007 IEEE Conference on Computer Vision and Pattern Recognition.

[23]  Yuan-Fang Wang,et al.  Stabilizing Stereo Correspondence Computation Using Delaunay Triangulation and Planar Homography , 2008, ISVC.

[24]  Pascal Fua,et al.  On benchmarking camera calibration and multi-view stereo for high resolution imagery , 2008, 2008 IEEE Conference on Computer Vision and Pattern Recognition.

[25]  Yuan-Fang Wang,et al.  Uniscale multi-view registration using double dog-leg method , 2009, Medical Imaging.

[26]  Yuan-Fang Wang,et al.  Feature detector and descriptor for medical images , 2009, Medical Imaging.

[27]  Manolis I. A. Lourakis,et al.  SBA: A software package for generic sparse bundle adjustment , 2009, TOMS.

[28]  Richard Szeliski,et al.  Building Rome in a day , 2009, 2009 IEEE 12th International Conference on Computer Vision.

[29]  J. Rabin,et al.  Visual Perception: A Clinical Orientation (4th ed.) , 2010 .