Robust Shape from Focus via Markov Random Fields

In this paper we study a problem of 3D scene reconstruction from a set of differently focused images, also known as the shape from focus (SFF) problem. Existing shape from focus methods are known to produce unstable depth estimates in areas with poor texture and in presence of strong highlights. So in this work we focus on the robustness of 3D scene structure recovery. We formulate a shape from focus problem in a Bayesian framework using Markov Random Fields and present an SFF method that yields a globally optimal surface with enforced smoothness priors. Although shape from focus has been studied for quite a long time there is no widely accepted test set for evaluation of SFF algorithms. Therefore we present a test set composed of 27 image sets with hand-labeled ground truth. We quantitatively evaluate our method on this test set and present the comparison results. These results demonstrate that our method is robust to highlights and untextured regions and that it outperforms the state-of-the-art.

[1]  H.N. Nair,et al.  Robust focus ranging , 1992, Proceedings 1992 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[2]  Muralidhara Subbarao,et al.  Accurate Recovery of Three-Dimensional Shape from Image Focus , 1995, IEEE Trans. Pattern Anal. Mach. Intell..

[3]  Shree K. Nayar,et al.  Shape from Focus , 1994, IEEE Trans. Pattern Anal. Mach. Intell..

[4]  Daniel Schaper.  Automated quality control for microtechnology components using a depth from focus approach , 2002, Proceedings Fifth IEEE Southwest Symposium on Image Analysis and Interpretation.

[5]  Richard Szeliski,et al.  A Comparative Study of Energy Minimization Methods for Markov Random Fields , 2006, ECCV.

[6]  Donald Geman,et al.  Stochastic relaxation, Gibbs distributions, and the Bayesian restoration of images , 1984 .

[7]  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).

[8]  Olga Veksler,et al.  Markov random fields with efficient approximations , 1998, Proceedings. 1998 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No.98CB36231).

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

[10]  Tae-Sun Choi,et al.  A heuristic approach for finding best focused shape , 2005, IEEE Transactions on Circuits and Systems for Video Technology.

[11]  Tarkan Aydin,et al.  A New Adaptive Focus Measure for Shape From Focus , 2008, BMVC.

[12]  Marie-Pierre Jolly,et al.  Interactive Graph Cuts for Optimal Boundary and Region Segmentation of Objects in N-D Images , 2001, ICCV.

[13]  Olga Veksler,et al.  Fast Approximate Energy Minimization via Graph Cuts , 2001, IEEE Trans. Pattern Anal. Mach. Intell..

[14]  Hailin Jin,et al.  A Variational Approach to Shape from Defocus , 2002, ECCV.

[15]  Murali Subbarao,et al.  Depth from defocus by changing camera aperture: a spatial domain approach , 1993, Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.

[16]  Markus Niederoest,et al.  Automatic 3D reconstruction and visualization of microscopic objects from a monoscopic multifocus image sequence , 2003 .

[17]  P. Grossmann,et al.  Depth from focus , 1987, Pattern Recognit. Lett..