Affine propagation for surface reconstruction in wide baseline stereo

The problem of dense matching in wide baseline stereo is considered. It is assumed that the scene is formed by piecewise-smooth, Lambertian, textured surfaces and that rectified images of the scene are available. We present a novel dense matching algorithm that accounts for local affine distortion and propagates the best matching affine parameters on each surface until a surface discontinuity is reached. Disparity maps and projective reconstructions for real-world wide baseline stereo images are shown.

[1]  Richard Szeliski,et al.  A Taxonomy and Evaluation of Dense Two-Frame Stereo Correspondence Algorithms , 2001, International Journal of Computer Vision.

[2]  Heiko Hirschmüller,et al.  Improvements in real-time correlation-based stereo vision , 2001, CVPR 2001.

[3]  Ioannis Pitas,et al.  Digital Image Processing Algorithms , 1993 .

[4]  Carlo Tomasi,et al.  Good features to track , 1994, 1994 Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.

[5]  Carlo Tomasi,et al.  Multiway cut for stereo and motion with slanted surfaces , 1999, Proceedings of the Seventh IEEE International Conference on Computer Vision.

[6]  Emanuele Trucco,et al.  Introductory techniques for 3-D computer vision , 1998 .

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

[8]  G. P. Otto,et al.  A "Region-Growing" Algorithm for Matching of Terrain Images , 1988, Alvey Vision Conference.

[9]  Adam Baumberg,et al.  Reliable feature matching across widely separated views , 2000, Proceedings IEEE Conference on Computer Vision and Pattern Recognition. CVPR 2000 (Cat. No.PR00662).

[10]  Jiri Matas,et al.  Robust wide-baseline stereo from maximally stable extremal regions , 2004, Image Vis. Comput..