Class-specific 3D localization using constellations of object parts

Improvement in acquisition systems, has resulted in the ability to capture more realistic 3D models of real world objects, creating a need for better data processing techniques, as in the case of text and images. In this paper, we address the issue of learning classspecific, deformable, 3D part-based structure for object part localization in 3D models/scenes. We employ an inference framework upon fully connected part-based graphs inspired by Pictorial Structures (PS), which combine the local appearance of parts and the long-range structural properties. Using efficient tools for learning the model and performing inference, we show good results on a variety of classes, outperforming PS [7] and ISM [15]. Further, a similar inference framework is employed to find dense correspondences between 3D models, seeded by the above object part localization. Our results show promise for application in more complex 3D processing tasks such as part retrieval, pose estimation, scene understanding and recognition.

[1]  Vladimir Kolmogorov,et al.  Convergent Tree-Reweighted Message Passing for Energy Minimization , 2006, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[2]  Amnon Shashua,et al.  Probabilistic graph and hypergraph matching , 2008, 2008 IEEE Conference on Computer Vision and Pattern Recognition.

[3]  Alexander M. Bronstein,et al.  Numerical Geometry of Non-Rigid Shapes , 2009, Monographs in Computer Science.

[4]  Judea Pearl,et al.  Probabilistic reasoning in intelligent systems - networks of plausible inference , 1991, Morgan Kaufmann series in representation and reasoning.

[5]  Ghassan Hamarneh,et al.  A Survey on Shape Correspondence , 2011, Comput. Graph. Forum.

[6]  Andrew W. Fitzgibbon,et al.  Real-time human pose recognition in parts from single depth images , 2011, CVPR 2011.

[7]  Daniel P. Huttenlocher,et al.  Beyond trees: common-factor models for 2D human pose recovery , 2005, Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1.

[8]  Leonidas J. Guibas,et al.  Shape Google: a computer vision approach to isometry invariant shape retrieval , 2009, 2009 IEEE 12th International Conference on Computer Vision Workshops, ICCV Workshops.

[9]  Bastian Leibe,et al.  Interleaved Object Categorization and Segmentation , 2003, BMVC.

[10]  Andrea Fusiello,et al.  A Bag of Words Approach for 3D Object Categorization , 2009, MIRAGE.

[11]  Pietro Perona,et al.  Object class recognition by unsupervised scale-invariant learning , 2003, 2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2003. Proceedings..

[12]  Aaron Hertzmann,et al.  Learning 3D mesh segmentation and labeling , 2010, SIGGRAPH 2010.

[13]  Daniel Cohen-Or,et al.  Salient geometric features for partial shape matching and similarity , 2006, TOGS.

[14]  Radu Horaud,et al.  SHREC '11: Robust Feature Detection and Description Benchmark , 2011, 3DOR@Eurographics.

[15]  Andrew E. Johnson,et al.  Using Spin Images for Efficient Object Recognition in Cluttered 3D Scenes , 1999, IEEE Trans. Pattern Anal. Mach. Intell..

[16]  Bernard Chazelle,et al.  Shape distributions , 2002, TOGS.

[17]  Szymon Rusinkiewicz,et al.  Rotation Invariant Spherical Harmonic Representation of 3D Shape Descriptors , 2003, Symposium on Geometry Processing.

[18]  Ko Nishino,et al.  Scale-hierarchical 3D object recognition in cluttered scenes , 2010, 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[19]  Luc Van Gool,et al.  Hough Transform and 3D SURF for Robust Three Dimensional Classification , 2010, ECCV.

[20]  Daniel P. Huttenlocher,et al.  Pictorial Structures for Object Recognition , 2004, International Journal of Computer Vision.

[21]  Jitendra Malik,et al.  Shape matching and object recognition using shape contexts , 2010, 2010 3rd International Conference on Computer Science and Information Technology.

[22]  Olivier Colot,et al.  A New 3D-Matching Method of Nonrigid and Partially Similar Models Using Curve Analysis , 2011, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[23]  Martial Hebert,et al.  A spectral technique for correspondence problems using pairwise constraints , 2005, Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1.

[24]  Vladimir Kolmogorov,et al.  Feature Correspondence Via Graph Matching: Models and Global Optimization , 2008, ECCV.

[25]  Max Welling,et al.  Learning in Markov Random Fields An Empirical Study , 2005 .

[26]  Martin A. Fischler,et al.  The Representation and Matching of Pictorial Structures , 1973, IEEE Transactions on Computers.

[27]  Nico Blodow,et al.  Fast Point Feature Histograms (FPFH) for 3D registration , 2009, 2009 IEEE International Conference on Robotics and Automation.

[28]  Luc Van Gool,et al.  Orientation invariant 3D object classification using hough transform based methods , 2010, 3DOR '10.

[29]  Leonidas J. Guibas,et al.  A concise and provably informative multi-scale signature based on heat diffusion , 2009 .