2016

SyncSpecCNN: Synchronized Spectral CNN for 3D Shape Segmentation

Yi, Li, Su, Hao, Guo, Xingwen et al.

Understand

In this paper, we study the problem of semantic annotation on 3D models that are represented as shape graphs.

A functional view is taken to represent localized information on graphs, so that annotations such as part segment or keypoint are nothing but 0-1 indicator vertex functions.
Compared with images that are 2D grids, shape graphs are irregular and non-isomorphic data structures.
To enable the prediction of vertex functions on them by convolutional neural networks, we resort to spectral CNN method that enables weight sharing by parameterizing kernels in the spectral domain spanned by graph laplacian eigenbases.

Built on

Segmentation of 3d meshes through spectral clustering
R. Liu and H. Zhang · 2004
Earlier work this paper cites.
Mesh segmentation via spectral embedding and contour analysis
R. Liu and H. Zhang · 2007
Earlier work this paper cites.
Learning 3d mesh segmentation and labeling
E. Kalogerakis, A. Hertzmann, and K. Singh · 2010
Earlier work this paper cites.
Angular synchronization by eigenvectors and semidefinite programming
A. Singer · 2011
Earlier work this paper cites.
Functional maps: a flexible representation of maps between shapes
M. Ovsjanikov, M. Ben-Chen, J. Solomon, A. Butscher, and L. Guibas · 2012
Earlier work this paper cites.
Spectral networks and locally connected networks on graphs
Original
J. Bruna, W. Zaremba, A. Szlam, and Y. LeCun · 2013
Earlier work this paper cites.
Fine-grained semi-supervised labeling of large shape collections
Q.-X. Huang, H. Su, and L. Guibas · 2013
Earlier work this paper cites.
Learning part-based templates from large collections of 3d shapes
V. G. Kim, W. Li, N. J. Mitra, S. Chaudhuri, S. DiVerdi, and T. Funkhouser · 2013
Earlier work this paper cites.
Image co-segmentation via consistent functional maps
F. Wang, Q. Huang, and L. J. Guibas · 2013
Earlier work this paper cites.
Shape2pose: human-centric shape analysis
V. G. Kim, S. Chaudhuri, L. Guibas, and T. Funkhouser · 2014
Earlier work this paper cites.

Similar

Learning 3d part detection from sparsely labeled data
A. Makadia and M. E. Yumer · 2014
Cited alongside, same era.
Unsupervised multi-class joint image segmentation
F. Wang, Q. Huang, M. Ovsjanikov, and L. J. Guibas · 2014
Cited alongside, same era.
Interactive shape co-segmentation via label propagation
Z. Wu, R. Shou, Y. Wang, and X. Liu · 2014
Cited alongside, same era.
3d shape segmentation and labeling via extreme learning machine
Z. Xie, K. Xu, L. Liu, and Y. Xiong · 2014
Cited alongside, same era.
Learning class-specific descriptors for deformable shapes using localized spectral convolutional networks
D. Boscaini, J. Masci, S. Melzi, M. M. Bronstein, U. Castellani, and P. Vandergheynst · 2015
Cited alongside, same era.
ShapeNet: An Information-Rich 3D Model Repository
Original
A. X. Chang, T. Funkhouser, L. Guibas, P. Hanrahan, Q. Huang, Z. Li, S. Savarese, M. Savva, S. Song, H. Su, J. Xiao, L. Yi, and F. Yu · 2015
Cited alongside, same era.
Convolutional networks on graphs for learning molecular fingerprints
D. K. Duvenaud, D. Maclaurin, J. Iparraguirre, R. Bombarell, T. Hirzel, A. Aspuru-Guzik, and R. P. Adams · 2015
Cited alongside, same era.
3d mesh labeling via deep convolutional neural networks
K. Guo, D. Zou, and X. Chen · 2015
Cited alongside, same era.
Deep convolutional networks on graph-structured data
Original
M. Henaff, J. Bruna, and Y. LeCun · 2015
Cited alongside, same era.
Spatial transformer networks
M. Jaderberg, K. Simonyan, A. Zisserman, et al · 2015
Cited alongside, same era.

Then

Fully convolutional networks for semantic segmentation
J. Long, E. Shelhamer, and T. Darrell · 2015
Later among the works it cites.
Geodesic convolutional neural networks on riemannian manifolds
J. Masci, D. Boscaini, M. Bronstein, and P. Vandergheynst · 2015
Later among the works it cites.
Voxnet: A 3d convolutional neural network for real-time object recognition
D. Maturana and S. Scherer · 2015
Later among the works it cites.
Going deeper with convolutions
C. Szegedy, W. Liu, Y. Jia, P. Sermanet, S. Reed, D. Anguelov, D. Erhan, V. Vanhoucke, and A. Rabinovich · 2015
Later among the works it cites.
Multi-scale context aggregation by dilated convolutions
Original
F. Yu and V. Koltun · 2015
Later among the works it cites.
Learning shape correspondence with anisotropic convolutional neural networks
Original
D. Boscaini, J. Masci, E. Rodolà, and M. M. Bronstein · 2016
Closest in time.
Convolutional neural networks on graphs with fast localized spectral filtering
Original
M. Defferrard, X. Bresson, and P. Vandergheynst · 2016
Closest in time.
Vertex-frequency analysis on graphs
D. I. Shuman, B. Ricaud, and P. Vandergheynst · 2016
Closest in time.
A scalable active framework for region annotation in 3d shape collections
L. Yi, V. G. Kim, D. Ceylan, I.-C. Shen, M. Yan, H. Su, C. Lu, Q. Huang, A. Sheffer, and L. Guibas · 2016
Closest in time.

Beyond the bibliography

alphaXiv searches the wider corpus for related work and actual follow-ups.

Open on alphaXiv

alphaXiv is searching for related work…

Reading the bibliography…