Improving Shape from Shading with Interactive Tabu Search
Optimisation based shape from shading (SFS) is sensitive to initialization: errors in initialization are a significant cause of poor overall shape reconstruction. In this paper, we present a method to help overcome this problem by means of user interaction. There are two key elements in our method. Firstly, we extend SFS to consider a set of initializations, rather than to use a single one. Secondly, we efficiently explore this initialization space using a heuristic search method, tabu search, guided by user evaluation of the reconstruction quality. Reconstruction results on both synthetic and real images demonstrate the effectiveness of our method in providing more desirable shape reconstructions.
Keywordsshape from shading user interaction tabu search
Unable to display preview. Download preview PDF.
- Belhumeur P N, Kriegman D J, Yuille A L. The basrelief ambiguity. International Journal of Computer Vision, 2001, 35: 1040–1046.Google Scholar
- Huang R, Smith W A P. Structure-preserving regularisation constraints for shape-from-shading. In Proc. the 13th International Conference on Computer Analysis of Images and Patterns, Sept. 2009, pp.865-872.Google Scholar
- Zeng G, Matsushita Y, Quan L, Shum H Y. Interactive shape from shading. In Proc. IEEE Computer Society Conference on Computer Vision and Pattern Recognition, June 2005, pp.343-350.Google Scholar
- Meyer A, Briceno H M, Bouakaz S. User-guided shape from shading to reconstruct fine details from a single photograph. In Proc. the 8th Asian Conference on Computer Vision, Nov. 2007, pp.738-747.Google Scholar
- Wu T P, Sun J, Tang C K, Shum H Y. Interactive normal reconstruction from a single image. ACM Transactions on Graphics, 2008, 27(5): Article No. 119.Google Scholar
- Saito H, Usami K. Shape from shading using genetic algorithm. In Proc. IECON, Nov. 1993, pp.1620-1625.Google Scholar
- Huang R, SmithWA P. Shape-from-shading under complex natural illumination. In Proc. the 18th IEEE International Conference on Image Processing, Sept. 2011, pp.13-16.Google Scholar
- Tomasi C, Manduchi R. Bilateral filtering for gray and color images. In Proc. IEEE International Conference on Computer Vision, Jan. 1998, pp.839-846.Google Scholar
- Xu L, Lu C, Xu Y, Jia J. Image smoothing via L0 gradient minimization. ACM Transactions on Graphics, 2011, 30(6): Article No. 174.Google Scholar
- Daniel P, Durou J D. From deterministic to stochastic methods for shape from shading. In Proc. the 4th Asian Conference on Computer Vision, Jan. 2000, pp.187-192.Google Scholar
- Falcone M, Sagona M. An algorithm for the global solution of the shape-from-shading model. In Proc. the 9th International Conference on Image Analysis and Processing, Sept. 1997, pp.596-603.Google Scholar