Multi-view attention-convolution pooling network for 3D point cloud classification

Wang, Wenju; Wang, Tao; Cai, Yu

doi:10.1007/s10489-021-02840-2

Cited by 10 publications

(5 citation statements)

References 43 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In another study, Wang et al [68] presented a multi-view attention-convolution pooling network (MVACPN) framework using Res2Net [69] to extract features from several 2D views. MVACPN effectively resolves the issues of feature information loss caused by feature representation and detail information loss during dimensionality reduction by employing the attention-convolution pooling method.…”

Section: Projection-based Methodsmentioning

confidence: 99%

A comprehensive overview of deep learning techniques for 3D point cloud classification and semantic segmentation

Sarker,

Stone

et al. 2024

Machine Vision and Applications

View full text Add to dashboard Cite

Point cloud analysis has a wide range of applications in many areas such as computer vision, robotic manipulation, and autonomous driving. While deep learning has achieved remarkable success on image-based tasks, there are many unique challenges faced by deep neural networks in processing massive, unordered, irregular and noisy 3D points. To stimulate future research, this paper analyzes recent progress in deep learning methods employed for point cloud processing and presents challenges and potential directions to advance this field. It serves as a comprehensive review on two major tasks in 3D point cloud processing-namely, 3D shape classification and semantic segmentation.

show abstract

Section: Projection-based Methodsmentioning

confidence: 99%

A comprehensive overview of deep learning techniques for 3D point cloud classification and semantic segmentation

Sarker,

Stone

et al. 2024

Machine Vision and Applications

View full text Add to dashboard Cite

show abstract

“…[43] aggregates similar features from multi-views through a recurrent clustering and pooling module, which enhances the recognition performance of multi-view 3D objects. In [44], a framework with multi-view attention-convolution pooling utilizes Res2Net to extract the features from multiple views to alleviate the information loss and strengthen the connection between these views. MVTN [45] designs a multi-view transformation network to exploit the optimal viewpoint s adaptively.…”

Section: Methods Based On Multi-viewmentioning

confidence: 99%

A Lightweight Network for Point Cloud Analysis via the Fusion of Local Features and Distribution Characteristics

Zheng

Sun

Chen

2022

Sensors

View full text Add to dashboard Cite

Effectively integrating the local features and their spatial distribution information for more effective point cloud analysis is a subject that has been explored for a long time. Inspired by convolutional neural networks (CNNs), this paper studies the relationship between local features and their spatial characteristics and proposes a concise architecture to effectively integrate them instead of designing more sophisticated feature extraction modules. Different positions in the feature map of the 2D image correspond to different weights in the convolution kernel, making the obtained features that are sensitive to local distribution characteristics. Thus, the spatial distribution of the input features of the point cloud within the receptive field is critical for capturing abstract regional aggregated features. We design a lightweight structure to extract local features by explicitly supplementing the distribution information of the input features to obtain distinctive features for point cloud analysis. Compared with the baseline, our model shows improvements in accuracy and convergence speed, and these advantages facilitate the introduction of the snapshot ensemble. Aiming at the shortcomings of the commonly used cosine annealing learning schedule, we design a new annealing schedule that can be flexibly adjusted for the snapshot ensemble technology, which significantly improves the performance by a large margin. Extensive experiments on typical benchmarks verify that, although it adopts the basic shared multi-layer perceptrons (MLPs) as feature extractors, the proposed model with a lightweight structure achieves on-par performance with previous state-of-the-art (SOTA) methods (e.g., MoldeNet40 classification, 0.98 million parameters and 93.5% accuracy; S3DIS segmentation, 1.4 million parameters and 68.7% mIoU).

show abstract

“…Literature [34] fuses the point cloud and RGB image, and voxelizes the raw point cloud which can form a frustum. Literature [35] uses Res2Net to extract the features from multiple 2D views and achieves higher classfication accuracy and better performance.…”

Section: Related Workmentioning

confidence: 99%

PointVotes: A Deep Learing Point Cloud Model for Tire Bubble Defect Detection

Yang¹,

Jiang²,

Nie³

et al. 2022

cai

View full text Add to dashboard Cite

In order to eliminate the hidden dangers caused by tire bubble defects, considering that the two-dimensional technology is sensitive to light, the 3D point cloud technology is used to obtain the tire surface morphology. This paper proposes a 3D point cloud network model named PointVotes, a point based target detection method. The designed structural framework includes: the fusion sampling layer, the voting layer and the proposal refinement layer. By observing the spatial characteristics of the detected target, a new point sampling method named C-farthest point sampling (C-FPS) is proposed. Combining with the fusion sampling strategy, the FPS and the C-FPS are sampled in a certain proportion. It solves the problem that the proposal box cannot be generated due to less available prospect information when generating suggestions for small targets. The network model uses Set Abstraction layers in multiple PointNet++ to extract features, arranges and combines features of different scales, forms high-dimensional features of points and votes, judges whether there are bubble defects through classification, and then generates proposals and regression to the prediction frame. Experiment results show that * Corresponding author PointVotes 1447 the mean average precision of the model can reach 82.8 % with a detection time of 0.12 s.

show abstract

Multi-view attention-convolution pooling network for 3D point cloud classification

Cited by 10 publications

References 43 publications

A comprehensive overview of deep learning techniques for 3D point cloud classification and semantic segmentation

A comprehensive overview of deep learning techniques for 3D point cloud classification and semantic segmentation

A Lightweight Network for Point Cloud Analysis via the Fusion of Local Features and Distribution Characteristics

PointVotes: A Deep Learing Point Cloud Model for Tire Bubble Defect Detection

Contact Info

Product

Resources

About