A Bayesian Framework for Simultaneous Matting and 3D Reconstruction

Conventional approaches to 3D scene reconstruction often treat matting and reconstruction as two separate problems, with matting a prerequisite to reconstruction. The problem with such an approach is that it requires taking irreversible decisions at the first stage, which may translate into reconstruction errors at the second stage. In this paper, we propose an approach which attempts to solve both problems jointly, thereby avoiding this limitation. A general Bayesian formulation for estimating opacity and depth with respect to a reference camera is developed. In addition, it is demonstrated that in the special case of binary opacity values (background/foreground) and discrete depth values, a global solution can be obtained via a single graph-cut computation. We demonstrate the application of the method to novel view synthesis in the case of a large-scale outdoor scene. An experimental comparison with a two-stage approach based on chroma-keying and shape-from-silhouette illustrates the advantages of the new method.

[1]  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).

[2]  Paul A. Viola,et al.  Roxels: responsibility weighted 3D volume reconstruction , 1999, Proceedings of the Seventh IEEE International Conference on Computer Vision.

[3]  A. Laurentini,et al.  The Visual Hull Concept for Silhouette-Based Image Understanding , 1994, IEEE Trans. Pattern Anal. Mach. Intell..

[4]  Kiriakos N. Kutulakos,et al.  A Theory of Shape by Space Carving , 2000, International Journal of Computer Vision.

[5]  Marcus A. Magnor,et al.  Joint 3D-reconstruction and background separation in multiple views using graph cuts , 2003, 2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2003. Proceedings..

[6]  Richard Szeliski,et al.  Stereo Matching with Transparency and Matting , 1999, International Journal of Computer Vision.

[7]  Steven M. Seitz,et al.  Photorealistic Scene Reconstruction by Voxel Coloring , 1997, International Journal of Computer Vision.

[8]  Richard Szeliski,et al.  High-quality video view interpolation using a layered representation , 2004, SIGGRAPH 2004.

[9]  Andrew Blake,et al.  Probabilistic Fusion of Stereo with Color and Contrast for Bilayer Segmentation , 2006, IEEE Trans. Pattern Anal. Mach. Intell..

[10]  VekslerOlga,et al.  Fast Approximate Energy Minimization via Graph Cuts , 2001 .

[11]  G. A. Thomas,et al.  Real-Time Camera Pose Estimation for Augmenting Sports Scenes , 2006 .

[12]  Vladimir Kolmogorov,et al.  An experimental comparison of min-cut/max- flow algorithms for energy minimization in vision , 2001, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[13]  Olga Veksler,et al.  Fast approximate energy minimization via graph cuts , 2001, Proceedings of the Seventh IEEE International Conference on Computer Vision.

[14]  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).

[15]  David Salesin,et al.  A Bayesian approach to digital matting , 2001, Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001.

[16]  Ingemar J. Cox,et al.  A maximum-flow formulation of the N-camera stereo correspondence problem , 1998, Sixth International Conference on Computer Vision (IEEE Cat. No.98CH36271).

[17]  Andrew W. Fitzgibbon,et al.  Bayesian Estimation of Layers from Multiple Images , 2002, ECCV.

[18]  Wojciech Matusik,et al.  Natural video matting using camera arrays , 2006, SIGGRAPH '06.

[19]  Rachid Deriche,et al.  Using Canny's criteria to derive a recursively implemented optimal edge detector , 1987, International Journal of Computer Vision.

[20]  R. Zabih,et al.  Exact voxel occupancy with graph cuts , 2000, Proceedings IEEE Conference on Computer Vision and Pattern Recognition. CVPR 2000 (Cat. No.PR00662).