Abstract
We propose new techniques for 2-D shape/contour completion, which is one of the important research topics related to shape analysis and computer vision, e.g. the detection of incomplete objects due to occlusion and noises. The purpose of shape completion is to find the optimal curve segments that fill the missing contour parts, so as to acquire the best estimation of the original complete object shapes. Unlike the previous work using local smoothness or minimum curvature priors, we solve the problem under a Bayesian formulation taking advantage of global shape prior knowledge. With the priors, our methods are expert in recovering significant shape structures and dealing with large occlusion cases. There are two different priors adopted in this paper: (i) A generic prior model that prefers minimal global shape transformation (including non-rigid deformation and affine transformation with respect to a reference object shape) of the recovered complete shape; and (ii) a class-specific shape prior model learned from training examples of an object category, which prefers the reconstructed shape to follow the learned shape variation models of the category. Efficient contour completion algorithms are suggested corresponding to the two types of priors. Our experimental results demonstrate the advantage of the proposed shape completion approaches compared to the existing techniques, especially for objects with complex structure under severe occlusion.
Article PDF
Similar content being viewed by others
Explore related subjects
Discover the latest articles, news and stories from top researchers in related subjects.Avoid common mistakes on your manuscript.
References
Rensink R A, Enns J T. Early completion of occluded objects. Vision Res, 1998, 38: 489–2505
Rutkowski W S. Shape completion. Comput Vis Graph Image Process, 1979, 9: 89–101
Ullman S. Filling-in the gaps: The shape of subjective contours and a model for their generation. Vision Res, 1976, 25: 1–6
Brady M, Grimson W. Shape encoding and subjective contours. Annu Natl Conf Artif Intell. Stanford, CA. USA, 1980. 15–17
Horn B K P. The curve of least energy. ACM Trans Math Softw, 1983, 9: 441–460
Mumford D. Elastica and computer vision. Algebr Geom Its Appl, 1994, 491–506
Sharon E, Brandt A, Basri R. Completion energies and scale. IEEE Trans Pattern Anal and Mach Intell, 2000, 22: 1117–1131
Mio W, Srivastava A, Liu X. Contour inferences for image understanding. Int J Comput Vis, 2006, 33: 137–144
Kimia B, Frankel I, Popescu A. Euler spiral for shape completion. Int J Comput Vis, 2003, 54: 157–180
Ben-Yosef G, Ben-Shahar O. Minimum length in the tangent bundle as a model for curve completion. In: IEEE Int Conf Comput Vis and Pattern Recogn. San Francisco, CA. USA, 2010. 2384–2391
Venkatesh M V, Cheung S S. Symmetric shape completion under severe occlusions. IEEE Int Conf Image Process, 2006, Atlanta, GA, USA. 709–712
Kanizsa G, Gerbino W. Amodal completion: Seeing or thinking? J. Beck (Ed.), Organ Represent Percept, 1982, 167–190
Thornber K K, Williams L R. Characterizing the distribution of completion shapes with corners using a mixture of random processes. Pattern Recogn, 2000, 33: 543–553
Ren X F, Fowlkes C C, Malik J. Learning probabilistic models for contour completion in natural images. Int J Comput Vis, 2008, 77: 47–63
Wang S, Stahl J S, Bailey A, et al. Global detection of salient convex boundaries. Int J Comput Vis, 2007, 71: 337–359
Cremers D, Rousson M, Deriche R. A review of statistical approaches to level set segmentation: Integrating color, texture, motion and shape. Int J Comput Vis, 2007, 72: 195–215
Harary G, Tal A. 3D Euler spirals for 3D curve completion. In: ACM Symp Comput Geom. Snowbird. Utah, USA, 2010. 393–402
Sharf A, Alexa M, Cohen-Or D. Context-based surface completion. ACM Trans Graph, 2004, 23: 878–887
Ilic S, Fua P. Implicit meshes for modeling and reconstruction. In: IEEE Int Conf Comput Vis Pattern Recogn, Madison. WI, USA, 2003. 2: 483–490
Jenke P, Wand M, Bokeloh M, et al. Bayesian point cloud reconstruction. Comput Graph Forum, 2006, 25: 337–359
Gal R, Shamir A, Hassner T, et al. Surface reconstruction using local shape priors. In: Eurographics Symp Geom Process. Barcelona, Spain, 2007. 253–262
Schnabel R, Degener P, Klein R. Completion and reconstruction with primitive shapes. Comput Graph Forum, 2009, 28: 503–512
Anguelov D, Srinivasan P, Koller D, et al. Scape: Shape completion and animation of people. ACM Trans Graph, 2005, 24: 408–416
Ferrari V, Tuytelaars T, Gool L V. Object detection by contour segment networks. Eur Conf Comput Vis, Graz, Austria, 2006, 14–28. Dataset: www.vision.ee.ethz.ch/~ferrari
Borenstein E, Sharon E, Ullman S. Combining top-down and bottom-up segmentation. IEEE Workshop Percept Organ Comput Vis, Washington, DC, USA, 2004, 46–53. Dataset: www.msri.org/people/members/eranb/
Chui H, Rangarajan A. A new point matching algorithm for non-rigid registration. Comput Vis Image Understand, 2003, 89: 114–141
Cootes T F, Taylor C J, Cooper D H, et al. Active shape models — their training and application. Comput Vis Image Understand, 1995, 61: 38–59
Riemenschneider H, Donoser M, Bischof H. Using partial edge contour matches for efficient object category localization. In: Eur Conf Comput Vis, Crete, Greece. 2010, Part V: 29–42
Author information
Authors and Affiliations
Corresponding author
Additional information
This article is published with open access at Springerlink.com
Rights and permissions
This article is published under an open access license. Please check the 'Copyright Information' section either on this page or in the PDF for details of this license and what re-use is permitted. If your intended use exceeds what is permitted by the license or if you are unable to locate the licence and re-use information, please contact the Rights and Permissions team.
About this article
Cite this article
Guo, G., Jiang, T., Wang, Y. et al. 2-D shape completion with shape priors. Chin. Sci. Bull. 58, 3430–3436 (2013). https://doi.org/10.1007/s11434-013-5946-4
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11434-013-5946-4