3,451 Hits in 5.8 sec

Multi-scale Receptive Fields Graph Attention Network for Point Cloud Classification [article]

Xi-An Li, Lei Zhang, Li-Yan Wang, Jian Lu
2020 arXiv   pre-print
In this paper, a multi-scale receptive fields graph attention network (named after MRFGAT) for point cloud classification is proposed.  ...  By focusing on the local fine features of point cloud and applying multi attention modules based on channel affinity, the learned feature map for our network can well capture the abundant features information  ...  graph attention networks for point cloud classification.  ... 
arXiv:2009.13289v1 fatcat:62jv22lunzai3iii3fdf42xjmi

Beyond single receptive field: A receptive field fusion-and-stratification network for airborne laser scanning point cloud classification

Yongqiang Mao, Kaiqiang Chen, Wenhui Diao, Xian Sun, Xiaonan Lu, Kun Fu, Martin Weinmann
2022 ISPRS journal of photogrammetry and remote sensing (Print)  
In this article, for the objective of configuring multi-receptive field features, we propose a novel receptive field fusion-and-stratification network (RFFS-Net).  ...  With receptive field fusion-and-stratification, RFFS-Net is more adaptable to the classification of regions with complex structures and extreme scale variations in large-scale ALS point clouds.  ...  However, these methods do not take into account the insufficiency of deep network receptive fields and the demand for multi-level receptive fields of urban-level ALS point clouds.  ... 
doi:10.1016/j.isprsjprs.2022.03.019 fatcat:tnkv5uuqbngxjlqtsro5yr5a64

Graph Attention Feature Fusion Network for ALS Point Cloud Classification

Jie Yang, Xinchang Zhang, Yun Huang
2021 Sensors  
Based on the graph attention mechanism, we first design a neighborhood feature fusion unit and an extended neighborhood feature fusion block, which effectively increases the receptive field for each point  ...  In this paper, we propose a graph attention feature fusion network (GAFFNet) that can achieve a satisfactory classification performance by capturing wider contextual information of the ALS point cloud.  ...  Acknowledgments: We would like to give thanks for the insightful comments and suggestions of the anonymous reviewers and the editor.  ... 
doi:10.3390/s21186193 pmid:34577396 pmcid:PMC8473412 fatcat:u6zp2vb3vzd2vkjc4gw4ywzjla

Semantic Segmentation for Point Cloud Scenes via Dilated Graph Feature Aggregation and Pyramid Decoders [article]

Yongqiang Mao, Xian Sun, Wenhui Diao, Kaiqiang Chen, Zonghao Guo, Xiaonan Lu, Kun Fu
2022 arXiv   pre-print
Due to the unicity of receptive field, semantic segmentation of point clouds remains challenging for the expression of multi-receptive field features, which brings about the misclassification of instances  ...  To configure multi-receptive field features, DGFA which takes the proposed dilated graph convolution (DGConv) as its basic building block, is designed to aggregate multi-scale feature representation by  ...  The universal point cloud segmentation networks (Qi et al. 2017b; Wang et al. 2019b ) employ the fixed KNN graph to search for neighboring points, so that the receptive field obtained by using input point  ... 
arXiv:2204.04944v2 fatcat:3iswkmkgbbfexi4sanoagpqfle

3DCTN: 3D Convolution-Transformer Network for Point Cloud Classification [article]

Dening Lu, Qian Xie, Linlin Xu, Jonathan Li
2022 arXiv   pre-print
This paper presents a novel hierarchical framework that incorporates convolution with Transformer for point cloud classification, named 3D Convolution-Transformer Network (3DCTN), to combine the strong  ...  Although accurate and fast point cloud classification is a fundamental task in 3D applications, it is difficult to achieve this purpose due to the irregularity and disorder of point clouds that make it  ...  To ensure the diversity of the receptive fields for sampling points, we construct multi-scale neighborhoods of each sampling point by query ball grouping [7] .  ... 
arXiv:2203.00828v1 fatcat:zlcs3l2xtfhivabprb5kjgysrm

PointAtrousGraph: Deep Hierarchical Encoder-Decoder with Point Atrous Convolution for Unorganized 3D Points [article]

Liang Pan, Chee-Meng Chew, Gim Hee Lee
2019 arXiv   pre-print
exploiting multi-scale edge features in point clouds.  ...  Similar with atrous convolution, our PAC can effectively enlarge receptive fields of filters and thus densely learn multi-scale point features.  ...  Our classification network (enclosed by red dashed lines in Fig. 4 ) aims to encode a global point feature vector by exploiting multi-scale local geometrical details in a point cloud.  ... 
arXiv:1907.09798v2 fatcat:gpyul44syfdbxfznbjmewjpdfa

PEMCNet: An Efficient Multi-Scale Point Feature Fusion Network for 3D LiDAR Point Cloud Classification

Genping Zhao, Weiguang Zhang, Yeping Peng, Heng Wu, Zhuowei Wang, Lianglun Cheng
2021 Remote Sensing  
However, most available multi-scale feature learning networks for large-scale 3D LiDAR point cloud classification tasks are time-consuming.  ...  The PEG unit enables us to progressively increase the receptive field for each observed point and aggregate the feature of a point cloud at different scales but without increasing computation.  ...  The multi-scale feature learning for the point cloud is realized by (1) introducing a novel point grouping method-PEG unit to capture multi-scale point features of flexibly varied receptive fields with  ... 
doi:10.3390/rs13214312 fatcat:hr2rc2i7kfd7pjutbxtqs3ozuy

CloudAttention: Efficient Multi-Scale Attention Scheme For 3D Point Cloud Learning [article]

Mahdi Saleh, Yige Wang, Nassir Navab, Benjamin Busam, Federico Tombari
2022 arXiv   pre-print
Finally, to mitigate the non-heterogeneity of point clouds, we propose an efficient Multi-Scale Tokenization (MST), which extracts scale-invariant tokens for attention operations.  ...  Spatial operations on large-scale point clouds, stored as sparse data, require extra cost. Attracted by the success of transformers, researchers are using multi-head attention for vision tasks.  ...  Earlier graph neural networks for point clouds are limited to node-level message passing and are impractical for large-scale point cloud applications.  ... 
arXiv:2208.00524v1 fatcat:26vbun6ynbdgvikbwdsnypeu7u

Deep Learning for LiDAR Point Clouds in Autonomous Driving: A Review [article]

Ying Li, Lingfei Ma, Zilong Zhong, Fei Liu, Dongpu Cao, Jonathan Li, Michael A. Chapman
2020 arXiv   pre-print
Although several published research papers focus on specific topics in computer vision for autonomous vehicles, to date, no general survey on deep learning applied in LiDAR point clouds for autonomous  ...  In this paper, we provide a systematic review of existing compelling deep learning architectures applied in LiDAR point clouds, detailing for specific tasks in autonomous driving such as segmentation,  ...  Besides, we also would like to thank anonymous reviewers for their insightful comments and suggestions.  ... 
arXiv:2005.09830v1 fatcat:zrja5sgtsvgulpnp7p7t4kxq54

DGANet: A Dilated Graph Attention-Based Network for Local Feature Extraction on 3D Point Clouds

Jie Wan, Zhong Xie, Yongyang Xu, Ziyin Zeng, Ding Yuan, Qinjun Qiu
2021 Remote Sensing  
To alleviate this problem, a Dilated Graph Attention-based Network (DGANet) with a certain feature for learning ability is proposed.  ...  Specifically, we first build a local dilated graph-like region for each input point to establish the long-range spatial correlation towards its corresponding neighbors, which allows the proposed network  ...  Acknowledgments: The authors thank the Stanford University for providing the experimental datasets. The authors also thank all editors and reviewers for their helpful comments and suggestions.  ... 
doi:10.3390/rs13173484 fatcat:ore6i4n2yncc3dmykjnim7cecy

Multi-scale Dynamic Graph Convolution Network for Point Clouds Classification

ZhengLi Zhai, Xin Zhang, LuYao Yao
2020 IEEE Access  
In this paper, we propose a Multi-scale Dynamic GCN model for point clouds classification, a Farthest Point Sampling method is applied in our model firstly to efficiently cover the entire point set, it  ...  Graph convolution network (GCN) has attracted more and more attention in recent years, especially in the field of non-Euclidean data processing.  ...  CONCLUSION In this paper, we proposed a Multi-scale Dynamic GCN model for point clouds classification, combined the Farthest Point Sampling algorithm and k-NN Graph method to sparse the whole point clouds  ... 
doi:10.1109/access.2020.2985279 fatcat:s74mrb4a3fdmfdzqstejglchli

TransLoc3D : Point Cloud based Large-scale Place Recognition using Adaptive Receptive Fields [article]

Tian-Xing Xu, Yuan-Chen Guo, Yu-Kun Lai, Song-Hai Zhang
2021 arXiv   pre-print
We also present a novel network architecture, named TransLoc3D, to obtain discriminative global descriptors of point clouds for the place recognition task.  ...  on the input point cloud.  ...  The following work SKNet [20] enhances this architecture using an attention mechanism to fuse multi-scale information from different receptive fields in 2D images.  ... 
arXiv:2105.11605v2 fatcat:s3zny5qnnbfipcfscpntxdr7ri

HPGNN: Using Hierarchical Graph Neural Networks for Outdoor Point Cloud Processing [article]

Arulmolivarman Thieshanthan, Amashi Niwarthana, Pamuditha Somarathne, Tharindu Wickremasinghe, Ranga Rodrigo
2022 arXiv   pre-print
Inspired by recent improvements in point cloud processing for autonomous navigation, we focus on using hierarchical graph neural networks for processing and feature learning over large-scale outdoor LiDAR  ...  This enables to learn over a large point cloud while retaining fine details that existing point-level graph networks struggle to achieve.  ...  Acknowledgement: We thank National Research Council of Sri Lanka for providing computational resources through the grant no. 19-080.  ... 
arXiv:2206.02153v1 fatcat:ijqtzzulivap7kjlnzroajuwci

AGNet: An Attention-Based Graph Network for Point Cloud Classification and Segmentation

Weipeng Jing, Wenjun Zhang, Linhui Li, Donglin Di, Guangsheng Chen, Jian Wang
2022 Remote Sensing  
To tackle this challenge, we propose a graph-based neural network with an attention pooling strategy (AGNet).  ...  Classification and segmentation of point clouds have attracted increasing attention in recent years. On the one hand, it is difficult to extract local features with geometric information.  ...  Acknowledgments: The authors want to thank Stanford University for providing the experimental datasets. Conflicts of Interest: The authors declare no conflict of interest.  ... 
doi:10.3390/rs14041036 fatcat:bekpvlrvpzhgnfclgc2pm5xukq

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

Qiang Zheng, Jian Sun, Wei Chen
2022 Sensors  
Thus, the spatial distribution of the input features of the point cloud within the receptive field is critical for capturing abstract regional aggregated features.  ...  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.  ...  Acknowledgments: The authors thank Stanford University for providing the experimental datasets. Conflicts of Interest: The authors declare no conflict of interest.  ... 
doi:10.3390/s22134742 pmid:35808253 pmcid:PMC9269399 fatcat:firdkpqxxrae3blb2oppg4swfq
« Previous Showing results 1 — 15 out of 3,451 results