PointNGCNN: Deep convolutional networks on 3D point clouds with neighborhood graph filters

Lü, Qiang; Chen, Chao; Xie, Wei; Luo, Yanlin

doi:10.1016/j.cag.2019.11.005

Cited by 38 publications

(15 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Modality Acc 3DShapeNets [1] volume 77.3% voxnet [16] volume 83% O-cnn [17] volume 89.9% Mvcnn [4] view 90.1% mlvcnn [19] view 94.16% Pointnet [5] Point cloud 77.6% Pointnet++ [6] Point cloud 89.2% PointNGCNN [31] Point cloud 92.8% Meshnet [22] Mesh 91% Ours with Graph Module Mesh 94.3% ± 0.5% FIGURE 9. Some misclassification results detected by the network structure of MeshNet with the KC function.…”

Section: Methodsmentioning

confidence: 99%

“…Similar to NGCNN [31], the correlation defined by the geodesic method can be extracted more effectively. In order to better define the connections within the normal vectors, the receptive field of the graph convolution is affected by the k-nearest geodesic neighbors algorithm, as inspired by the ESOD method of Hubeli [10].…”

Section: K-nearest Geodesic Neighbors (Kngn)mentioning

confidence: 99%

See 1 more Smart Citation

MeshGraphNet: An Effective 3D Polygon Mesh Recognition With Topology Reconstruction

Song

et al. 2020

IEEE Access

View full text Add to dashboard Cite

Section: Methodsmentioning

confidence: 99%

Section: K-nearest Geodesic Neighbors (Kngn)mentioning

confidence: 99%

MeshGraphNet: An Effective 3D Polygon Mesh Recognition With Topology Reconstruction

Song

et al. 2020

IEEE Access

View full text Add to dashboard Cite

“…In the segmentation task, Li [18] applies graph convolution into the semantic segmentation task use Laplacian to perform reasoning directly to the feature space. Lu [19] generates a neighborhood graph that shows the relationship for each point's neighboring points and then filters the neighborhood graph using Chebyshev polynomials. Hakim [11] introduced a graph Laplacian regularizer, which divides the image into two regions by measuring graph laplacians on the vessels and their backgrounds.…”

Section: Related Workmentioning

confidence: 99%

Improvement for Single Image Super-resolution and Image Segmentation by Graph Laplacian Regularizer Based on Differences of Neighboring Pixels

2022

IJIES

View full text Add to dashboard Cite

The neighboring relationship of the pixels is fundamental information in the image. Utilizing neighboring pixel information provides an advantage over using only pixel-to-pixel information. This study presents a regularization term based on the differences of neighboring pixels. We define the differences of neighboring pixels by using the Graph Theory approach. We then propose an effective graph Laplacian regularization to enforce the differences between pixels as the nodes and differences between nodes as edges. In our scheme, Graph Laplacian constructs from the output of the convolutional neural network and ground-truth image. The generated differences matrices from the output and ground-truth are combined as a Laplacian regularization term used as the deep convolutional neural network's new objective function. Experiments show that our scheme successfully captures pixel neighbor relations and improves the performance of the convolutional neural network better than the baseline without a regularization term. Qualitative and quantitative results show that our developed regularizer proved to enhance the boundary structure on image super-resolution and image segmentation tasks, which is achieved Structural Similarity Index (SSIM) of 0.9604 and 0.8263 on Cartoon set and Manga109 datasets and area under the curve (AUC) of 0.9740 and 0.9561 on DRIVE and STARE datasets, respectively.

show abstract

“…Recently, DGCNN [26] and its variant [27] well utilized the graph network with respect to the edges' convolution on points and then obtained the local edges' information of point cloud. Other relevant works applying the graph structure of point cloud can be found in [28][29][30].…”

Section: Introductionmentioning

confidence: 99%

Multiscale Receptive Fields Graph Attention Network for Point Cloud Classification

Wang

Lü³

2021

Complexity

View full text Add to dashboard Cite

Understanding the implication of point cloud is still challenging in the aim of classification or segmentation for point cloud due to its irregular and sparse structure. As we have known, PointNet architecture as a ground-breaking work for point cloud process can learn shape features directly on unordered 3D point cloud and has achieved favorable performance, such as 86% mean accuracy and 89.2% overall accuracy for classification task, respectively. However, this model fails to consider the fine-grained semantic information of local structure for point cloud. Then, a multiscale receptive fields graph attention network (named after MRFGAT) by means of semantic features of local patch for point cloud is proposed in this paper, and the learned feature map for our network can well capture the abundant features information of point cloud. The proposed MRFGAT architecture is tested on ModelNet datasets, and results show it achieves state-of-the-art performance in shape classification tasks, such as it outperforms GAPNet (Chen et al.) model by 0.1% in terms of OA and compete with DGCNN (Wang et al.) model in terms of MA.

show abstract

PointNGCNN: Deep convolutional networks on 3D point clouds with neighborhood graph filters

Cited by 38 publications

References 6 publications

MeshGraphNet: An Effective 3D Polygon Mesh Recognition With Topology Reconstruction

MeshGraphNet: An Effective 3D Polygon Mesh Recognition With Topology Reconstruction

Improvement for Single Image Super-resolution and Image Segmentation by Graph Laplacian Regularizer Based on Differences of Neighboring Pixels

Multiscale Receptive Fields Graph Attention Network for Point Cloud Classification

Contact Info

Product

Resources

About