3D stereoscopic image pairs by depth-map generation

This work presents a new unsupervised technique aimed to generate stereoscopic views estimating depth information from a single input image. Using a single input image, vanishing lines/points are extracted using a few heuristics to generate an approximated depth map. The depth map is then used to generate stereo pairs. The overall method is well suited for real time application and works also on CFA (colour filtering array) data acquired by consumer imaging devices. Experimental results on a large dataset are reported.

[1]  John R. Smith,et al.  Image Classification and Querying Using Composite Region Templates , 1999, Comput. Vis. Image Underst..

[2]  Filippo Vella,et al.  3D effect generation from monocular view , 2002, Proceedings. First International Symposium on 3D Data Processing Visualization and Transmission.

[3]  Sebastiano Battiato,et al.  An Introduction to the Digital Still Camera Technology , 2001 .

[4]  Dorin Comaniciu,et al.  Robust analysis of feature spaces: color image segmentation , 1997, Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[5]  Antonio Criminisi,et al.  Accurate Visual Metrology from Single and Multiple Uncalibrated Images , 2001, Distinguished Dissertations.

[6]  Ian P. Howard,et al.  Binocular Vision and Stereopsis , 1996 .

[7]  Sebastiano Battiato,et al.  Depth map generation by image classification , 2004, IS&T/SPIE Electronic Imaging.

[8]  Dana H. Ballard,et al.  Computer Vision , 1982 .

[9]  V. Cantoni,et al.  Vanishing point detection: representation analysis and new approaches , 2001, Proceedings 11th International Conference on Image Analysis and Processing.

[10]  J.R. Smith,et al.  Decoding image semantics using composite region templates , 1998, Proceedings. IEEE Workshop on Content-Based Access of Image and Video Libraries (Cat. No.98EX173).

[11]  Roberto Cipolla,et al.  3D models of architectural scenes from uncalibrated images and vanishing points , 1999, Proceedings 10th International Conference on Image Analysis and Processing.