Non-rigid 3D Object Retrieval with a Learned Shape Descriptor

Non-rigid 3D objects are difficult to distinguish due to the structural transformation and noises. In this paper we develop a novel method to learn a discriminative shape descriptor for non-rigid 3D object retrieval. Compact low-level shape descriptors are designed from spectral descriptor, and the non-linear mapping of low level shape descriptors is carried out by a Siamese network. The Siamese network is trained to maximize the inter-class margin and minimize the intra-class distance. With an appropriate network hierarchy, we extract the last layer of the successfully trained network as the high-level shape descriptor. Furthermore, we successfully combine two low-level shape descriptors, based on the Heat Kernel Signature and the Wave Kernel Signature, and test the method on the benchmark dataset SHREC’14 Non-Rigid 3D Human Models. Experimental results show our method outperforms most of the existing algorithms for 3D shape retrieval.

[1]  Guillaume Lavoué,et al.  Combination of bag-of-words descriptors for robust partial shape retrieval , 2012, The Visual Computer.

[2]  Dietmar Saupe,et al.  3D Model Retrieval with Spherical Harmonics and Moments , 2001, DAGM-Symposium.

[3]  Andrea Torsello,et al.  A statistical model of Riemannian metric variation for deformable shape analysis , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[4]  Song Bai,et al.  Deep learning representation using autoencoder for 3D shape retrieval , 2014, SPAC.

[5]  Bo Li,et al.  Shape Retrieval of Non-Rigid 3D Human Models , 2014, 3DOR@Eurographics.

[6]  Ming Ouhyoung,et al.  On Visual Similarity Based 3D Model Retrieval , 2003, Comput. Graph. Forum.

[7]  Iasonas Kokkinos,et al.  Scale-invariant heat kernel signatures for non-rigid shape recognition , 2010, 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[8]  Hao Zhang,et al.  A spectral approach to shape-based retrieval of articulated 3D models , 2007, Comput. Aided Des..

[9]  Alexander M. Bronstein,et al.  Supervised learning of bag‐of‐features shape descriptors using sparse coding , 2014, Comput. Graph. Forum.

[10]  Yann LeCun,et al.  Signature Verification Using A "Siamese" Time Delay Neural Network , 1993, Int. J. Pattern Recognit. Artif. Intell..

[11]  Michael Elad,et al.  Content based retrieval of VRML objects: an iterative and interactive approach , 2002 .

[12]  Daniel Cremers,et al.  Non-rigid 3D Shape Retrieval via Large Margin Nearest Neighbor Embedding , 2016, ECCV.

[13]  Rahul Sukthankar,et al.  MatchNet: Unifying feature and metric learning for patch-based matching , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[14]  Meng Wang,et al.  3D deep shape descriptor , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[15]  Raif M. Rustamov,et al.  Laplace-Beltrami eigenfunctions for deformation invariant shape representation , 2007 .

[16]  Daniel Cremers,et al.  The wave kernel signature: A quantum mechanical approach to shape analysis , 2011, 2011 IEEE International Conference on Computer Vision Workshops (ICCV Workshops).

[17]  Dietmar Saupe,et al.  Tools for 3D-object retrieval: Karhunen-Loeve transform and spherical harmonics , 2001, 2001 IEEE Fourth Workshop on Multimedia Signal Processing (Cat. No.01TH8564).

[18]  Yann LeCun,et al.  Learning a similarity metric discriminatively, with application to face verification , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[19]  Paul Suetens,et al.  A comparison of methods for non-rigid 3D shape retrieval , 2013, Pattern Recognit..

[20]  Edward K. Wong,et al.  Deepshape: Deep learned shape descriptor for 3D shape matching and retrieval , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[21]  Ming Yang,et al.  DeepFace: Closing the Gap to Human-Level Performance in Face Verification , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[22]  Yi Fang,et al.  Learning a discriminative deformation-invariant 3D shape descriptor via many-to-one encoder , 2016, Pattern Recognit. Lett..

[23]  Nikos Komodakis,et al.  Learning to compare image patches via convolutional neural networks , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[24]  Yann LeCun,et al.  Computing the stereo matching cost with a convolutional neural network , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[25]  Leonidas J. Guibas,et al.  Shape google: Geometric words and expressions for invariant shape retrieval , 2011, TOGS.

[26]  Rongrong Ji,et al.  Learning High-Level Feature by Deep Belief Networks for 3-D Model Retrieval and Recognition , 2014, IEEE Transactions on Multimedia.

[27]  Serge J. Belongie,et al.  Learning deep representations for ground-to-aerial geolocalization , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

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