Local Spectral Graph Convolution for Point Set Feature Learning

@inproceedings{Wang2018LocalSG,
  title={Local Spectral Graph Convolution for Point Set Feature Learning},
  author={Chu Wang and Babak Samari and Kaleem Siddiqi},
  booktitle={ECCV},
  year={2018}
}
Feature learning on point clouds has shown great promise, with the introduction of effective and generalizable deep learning frameworks such as pointnet. [...] Key Method In our approach, graph convolution is carried out on a nearest neighbor graph constructed from a point's neighborhood, such that features are jointly learned.Expand
Point Attention Network for Semantic Segmentation of 3D Point Clouds
TLDR
The proposed point attention network consists of an encoder and decoder which, together with the LAE-Conv layers and the point-wise spatial attention modules, make it an end-to-end trainable network for predicting dense labels for 3D point cloud segmentation. Expand
TGNet: Geometric Graph CNN on 3-D Point Cloud Segmentation
TLDR
A novel graph convolution architecture, which is term as Taylor Gaussian mixture model (GMM) network (TGNet), is proposed, to efficiently learn expressive and compositional local geometric features from point clouds. Expand
PointNGCNN: Deep convolutional networks on 3D point clouds with neighborhood graph filters
TLDR
A novel end-to-end deep learning network called PointNGCNN is developed that can consume point clouds for 3D object recognition and segmentation tasks and has achieved good performance in the recognition and segmentsation tasks. Expand
Point Clouds Learning Using Directed Connected Graph
TLDR
A directed connectedgraph network (DCGN) is proposed, which can effectively capture the spatial relationship of local point sets by constructing the directed connected graph (DCG) and use a distance-weighted method to perform local feature fusion. Expand
Local Learning in Point Clouds based on Spectral Pooling
  • Yushi Li, G. Baciu
  • Computer Science
  • 2020 IEEE 19th International Conference on Cognitive Informatics & Cognitive Computing (ICCI*CC)
  • 2020
TLDR
This paper proposes to integrate a local point convolution network with spectral pooling to aggregate and learn features in 3D point clouds and its benefits are fast convergence and competitive performance on point cloud classification. Expand
PointVGG: Graph convolutional network with progressive aggregating features on point clouds
TLDR
A novel network, namely, PointVGG, with Pconv, Ppool, and graph structure for feature learning of point clouds, is presented and applied to object classification and part segmentation. Expand
Point Clouds Learning with Attention-based Graph Convolution Networks
TLDR
This work proposes a novel network structure, named Attention-based Graph Convolution Networks (AGCN), to extract point clouds features, taking the learning process as a message propagation between adjacent points for analyzing the relationships between local features of the points. Expand
LSANet: Feature Learning on Point Sets by Local Spatial Attention
TLDR
This work designs a novel Local Spatial Attention (LSA) module to adaptively generate attention maps according to the spatial distribution of local regions and proposes the Spatial Feature Extractor (SFE), which constructs a branch architecture, to aggregate the spatial information with associated features in each layer of the network better. Expand
FFPointNet: Local and global fused feature for 3D point clouds analysis
TLDR
A novel module, ChannelNet, a simple and effective module that exploits global shape features using 1D convolutions using only 0.041 million parameters is designed, making it easy to plug in the generic PointNet++ backbone to exploits both local and global shape structures for better contextual representation. Expand
Multi-Scale Neighborhood Feature Extraction and Aggregation for Point Cloud Segmentation
TLDR
This paper proposes a Multi-scale Neighborhood Feature Extraction and Aggregation Model (MNFEAM) to enhance feature extraction for point cloud learning that tries to first extract multi-scale neighborhood information for each input point and then aggregate local information of a mid-level locality feature space, and finally integrate the aggregated local and the global feature vectors. Expand
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 22 REFERENCES
PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space
TLDR
A hierarchical neural network that applies PointNet recursively on a nested partitioning of the input point set and proposes novel set learning layers to adaptively combine features from multiple scales to learn deep point set features efficiently and robustly. Expand
PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation
TLDR
This paper designs a novel type of neural network that directly consumes point clouds, which well respects the permutation invariance of points in the input and provides a unified architecture for applications ranging from object classification, part segmentation, to scene semantic parsing. Expand
Geometric Deep Learning on Graphs and Manifolds Using Mixture Model CNNs
TLDR
This paper proposes a unified framework allowing to generalize CNN architectures to non-Euclidean domains (graphs and manifolds) and learn local, stationary, and compositional task-specific features and test the proposed method on standard tasks from the realms of image-, graph-and 3D shape analysis and show that it consistently outperforms previous approaches. Expand
Dominant Set Clustering and Pooling for Multi-View 3D Object Recognition
TLDR
A recurrent clustering and pooling module that boosts performance for multi-view 3D object recognition, achieving a new state of the art test set recognition accuracy of 93.8% on the ModelNet 40 database. Expand
SyncSpecCNN: Synchronized Spectral CNN for 3D Shape Segmentation
TLDR
This paper introduces a spectral parametrization of dilated convolutional kernels and a spectral transformer network that enables weight sharing by parametrizing kernels in the spectral domain spanned by graph Laplacian eigenbases and strives to overcome two key challenges: how to share coefficients and conduct multi-scale analysis in different parts of the graph for a single shape. Expand
Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering
TLDR
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. Expand
3D ShapeNets: A deep representation for volumetric shapes
TLDR
This work proposes to represent a geometric 3D shape as a probability distribution of binary variables on a 3D voxel grid, using a Convolutional Deep Belief Network, and shows that this 3D deep representation enables significant performance improvement over the-state-of-the-arts in a variety of tasks. Expand
FOCUSR: Feature Oriented Correspondence Using Spectral Regularization--A Method for Precise Surface Matching
TLDR
An improved algorithm for dense vertex-to-vertex correspondence that uses direct matching of features defined on a surface and improves it by using spectral correspondence as a regularization, which greatly improves the matching precision while performing at much greater speed than existing methods. Expand
Normalized cuts and image segmentation
  • Jianbo Shi, J. Malik
  • Mathematics, Computer Science
  • Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition
  • 1997
TLDR
This work treats image segmentation as a graph partitioning problem and proposes a novel global criterion, the normalized cut, for segmenting the graph, which measures both the total dissimilarity between the different groups as well as the total similarity within the groups. Expand
ScanNet: Richly-Annotated 3D Reconstructions of Indoor Scenes
TLDR
This work introduces ScanNet, an RGB-D video dataset containing 2.5M views in 1513 scenes annotated with 3D camera poses, surface reconstructions, and semantic segmentations, and shows that using this data helps achieve state-of-the-art performance on several 3D scene understanding tasks. Expand
...
1
2
3
...