Measuring the Self-Consistency of Stereo Algorithms

A new approach to characterizing the performance of point-correspondence algorithms is presented. Instead of relying on any "ground truth', it uses the self-consistency of the outputs of an algorithm independently applied to different sets of views of a static scene. It allows one to evaluate algorithms for a given class of scenes, as well as to estimate the accuracy of every element of the output of the algorithm for a given set of views. Experiments to demonstrate the usefulness of the methodology are presented.

[1]  Richard Szeliski,et al.  Prediction error as a quality metric for motion and stereo , 1999, Proceedings of the Seventh IEEE International Conference on Computer Vision.

[2]  Takeo Kanade,et al.  A Stereo Matching Algorithm with an Adaptive Window: Theory and Experiment , 1994, IEEE Trans. Pattern Anal. Mach. Intell..

[3]  Pascal Fua,et al.  Self-Consistency: A Novel Approach to Characterizing the Accuracy and Reliability of Point Correspon , 1998, ICCV 1999.

[4]  Peter Meer,et al.  Performance Assessment Through Bootstrap , 1997, IEEE Trans. Pattern Anal. Mach. Intell..

[5]  Olivier D. Faugeras,et al.  Characterizing the Uncertainty of the Fundamental Matrix , 1997, Comput. Vis. Image Underst..

[6]  Richard Szeliski,et al.  An Experimental Comparison of Stereo Algorithms , 1999, Workshop on Vision Algorithms.

[7]  Pascal Fua,et al.  Characterizing the Performance of Multiple-Image Point-Correspondence Algorithms Using Self-Consistency , 1999, Workshop on Vision Algorithms.

[8]  Pascal Fua,et al.  A Framework for Detecting Changes in Terrain , 1998 .

[9]  Long Quan,et al.  Relative 3D Reconstruction Using Multiple Uncalibrated Images , 1993, Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.

[10]  Richard Szeliski,et al.  Recovering 3D Shape and Motion from Image Streams Using Nonlinear Least Squares , 1994, J. Vis. Commun. Image Represent..

[11]  Pascal Fua,et al.  Detecting changes in 3-D shape using self-consistency , 2000, Proceedings IEEE Conference on Computer Vision and Pattern Recognition. CVPR 2000 (Cat. No.PR00662).

[12]  Pascal Fua,et al.  Combining Stereo and Monocular Information to Compute Dense Depth Maps that Preserve Depth Discontinuities , 1991, IJCAI.

[13]  Pascal Fua,et al.  Quantitative and Qualitative Comparison of Some Area and Feature-based Stereo Algorithms , 1992 .

[14]  Long Quan,et al.  Relative 3D Reconstruction Using Multiple Uncalibrated Images , 1995, Int. J. Robotics Res..

[15]  Andrew Zisserman,et al.  Performance characterization of fundamental matrix estimation under image degradation , 1997, Machine Vision and Applications.