SyncSpecCNN: Synchronized Spectral CNN for 3D Shape Segmentation

  title={SyncSpecCNN: Synchronized Spectral CNN for 3D Shape Segmentation},
  author={L. Yi and Hao Su and Xingwen Guo and Leonidas J. Guibas},
  journal={2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
  • L. YiHao Su L. Guibas
  • Published 2 December 2016
  • Computer Science
  • 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
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… 

Figures and Tables from this paper

Revisiting 2D Convolutional Neural Networks for Graph-based Applications

This paper proposes two novel graph-to-grid mapping schemes, namely, graph-preserving grid layout and its extension Hierarchical GPGL for computational efficiency and proposes a novel vertex separation penalty that encourages graph vertices to lay on the grid without any overlap.

3D shape segmentation via shape fully convolutional networks

CoSegNet: Deep Co-Segmentation of 3D Shapes with Group Consistency Loss

CoSegNet takes as input a set of unsegmented shapes, proposes per-shape parts, and then jointly optimizes the part labelings across the set subjected to a novel group consistency loss expressed via matrix rank estimates.

RGCNN: Regularized Graph CNN for Point Cloud Segmentation

A regularized graph convolutional neural network (RGCNN) that directly consumes point clouds is proposed that significantly reduces the computational complexity while achieving competitive performance with the state of the art.

Cross-Shape Graph Convolutional Networks

The results show significantly improved performance for 3D point cloud semantic segmentation compared to conventional approaches, especially in cases with the limited number of training examples.

Learning to Segment 3D Point Clouds in 2D Image Space

This paper studies the problem of how to effectively and efficiently project such point clouds into a 2D image space so that traditional 2D convolutional neural networks such as U-Net can be applied for segmentation and proposes a novel hierarchical approximate algorithm.

Neural 3D Morphable Models: Spiral Convolutional Networks for 3D Shape Representation Learning and Generation

This work introduces a novel graph convolutional operator, acting directly on the 3D mesh, that explicitly models the inductive bias of the fixed underlying graph, by enforcing consistent local orderings of the vertices of the graph, through the spiral operator.

VoxSegNet: Volumetric CNNs for Semantic Part Segmentation of 3D Shapes

  • Zongji WangFeng Lu
  • Computer Science
    IEEE Transactions on Visualization and Computer Graphics
  • 2020
Experimental results demonstrate that promising results can be achieved by using volumetric data, with part segmentation accuracy comparable or superior to state-of-the-art non-volumetric methods.

Deep Functional Dictionaries: Learning Consistent Semantic Structures on 3D Models from Functions

Even though the authors' shapes have independent discretizations and no functional correspondences are provided, the network is able to generate latent bases, in a consistent order, that reflect the shared semantic structure among the shapes.



Learning shape correspondence with anisotropic convolutional neural networks

An intrinsic convolutional neural network architecture based on anisotropic diffusion kernels is introduced, which is term Anisotropic Convolutional Neural Network (ACNN), and is used to effectively learn intrinsic dense correspondences between deformable shapes in very challenging settings.

Learning class‐specific descriptors for deformable shapes using localized spectral convolutional networks

Experimental results show that the proposed approach allows learning class‐specific shape descriptors significantly outperforming recent state‐of‐the‐art methods on standard benchmarks.

3D Mesh Labeling via Deep Convolutional Neural Networks

Experimental results on several public benchmarks show that the proposed approach is robust for various 3D meshes, and outperforms state-of-the-art approaches as well as classic learning algorithms in recognizing mesh labels.

Learning 3D Part Detection from Sparsely Labeled Data

An algorithm that combines independently trained part classifiers with a structured SVM model, inspired by structured multi-class object detection models for images, is developed and shows promising results on real-world textured 3D data.

ShapeNet: An Information-Rich 3D Model Repository

ShapeNet contains 3D models from a multitude of semantic categories and organizes them under the WordNet taxonomy, a collection of datasets providing many semantic annotations for each 3D model such as consistent rigid alignments, parts and bilateral symmetry planes, physical sizes, keywords, as well as other planned annotations.

Fully convolutional networks for semantic segmentation

The key insight is to build “fully convolutional” networks that take input of arbitrary size and produce correspondingly-sized output with efficient inference and learning.

Spectral Networks and Locally Connected Networks on Graphs

This paper considers possible generalizations of CNNs to signals defined on more general domains without the action of a translation group, and proposes two constructions, one based upon a hierarchical clustering of the domain, and another based on the spectrum of the graph Laplacian.

Deep Convolutional Networks on Graph-Structured Data

This paper develops an extension of Spectral Networks which incorporates a Graph Estimation procedure, that is test on large-scale classification problems, matching or improving over Dropout Networks with far less parameters to estimate.

Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering

This work presents a formulation of CNNs in the context of spectral graph theory, which provides the necessary mathematical background and efficient numerical schemes to design fast localized convolutional filters on graphs.

A scalable active framework for region annotation in 3D shape collections

This work proposes a novel active learning method capable of enriching massive geometric datasets with accurate semantic region annotations, and demonstrates that incorporating verification of all produced labelings within this unified objective improves both accuracy and efficiency of the active learning procedure.