LPCCNet: A Lightweight Network for Point Cloud Classification

Li, Minle; Hu, Yihua; Zhao, Nanxiang; Guo, Liren

doi:10.1109/lgrs.2018.2889472

Cited by 4 publications

(2 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Since PointNet [10] pioneered the direct extraction of features from disordered points, deep learning-based architectures have been widely employed in the 3D vision domain. The success of several follow-up works [11][12][13][14][15] has shown the enormous potential of this method. Based on the architecture of PointNet++ [16], PU-Net [17] concatenated features of different scales in a weighted manner at the patch level and then used the convolutional layer for feature expansion.…”

Section: Introductionmentioning

confidence: 99%

PU-CTG: A Point Cloud Upsampling Network Using Transformer Fusion and GRU Correction

Li,

Lin,

Cheng

et al. 2024

Remote Sensing

View full text Add to dashboard Cite

Point clouds are widely used in remote sensing applications, e.g., 3D object classification, semantic segmentation, and building reconstruction. Generating dense and uniformly distributed point clouds from low-density ones is beneficial to 3D point cloud applications. The traditional methods mainly focus on the global shape of 3D point clouds, thus ignoring detailed representations. The enhancement of detailed features is conducive to generating dense and uniform point clouds. In this paper, we propose a point cloud upsampling network to improve the detail construction ability, named PU-CTG. The proposed method is implemented by a cross-transformer-fused module and a GRU-corrected module. The aim of the cross-transformer module is to enable the interaction and effective fusion between different scales of features so that the network can capture finer features. The purpose of the gated recurrent unit (GRU) is to reconstruct fine-grained features by rectifying the feedback error. The experimental results demonstrate the effectiveness of our method. Furthermore, the ModelNet40 dataset is upsampled by PU-CTG, and the classification experiment is applied to PointNet to verify the promotion ability of this network.

show abstract

Section: Introductionmentioning

confidence: 99%

PU-CTG: A Point Cloud Upsampling Network Using Transformer Fusion and GRU Correction

Li,

Lin,

Cheng

et al. 2024

Remote Sensing

View full text Add to dashboard Cite

show abstract

“…The rapid development of 3D sensors has increased the demand for point cloud processing technology. At present, point cloud processing technology is widely used in sensor systems such as AR, autonomous driving, and pose estimation 1 – 3 In recent years, deep learning methods are widely used in point cloud processing and have achieved good results 4 – 6 . Because a single point cannot provide enough information to identify a local structure, neighborhood search technology is very important in point cloud analysis.…”

Section: Introductionmentioning

confidence: 99%

Adaptive deep learning-based neighborhood search method for point cloud

Xiang

Wen

2022

Sci Rep

View full text Add to dashboard Cite

Point cloud processing is a highly challenging task in 3D vision because it is unstructured and unordered. Recently, deep learning has been proven to be quite successful in point cloud recognition, registration, segmentation, etc. Neighborhood search operation is an important component of point cloud deep learning models, and directly affects the performance of the model. In this paper, we propose a learnable neighborhood search method. This method adaptively chooses an appropriate search method based on the characteristics of each point, thus avoiding the disadvantage of selecting the search method manually. We validate the proposed methods on ModelNet40 dataset and ShapeNetPart dataset, and all the chosen models achieved a performance improvement with a maximum improvement of 1.1%. The proposed method is a plug-and-play technique and can be easily integrated into existing methods.

show abstract

Convolutional neural networks with hybrid weights for 3D point cloud classification

Cao

2021

Appl Intell

View full text Add to dashboard Cite

LPCCNet: A Lightweight Network for Point Cloud Classification

Cited by 4 publications

References 10 publications

PU-CTG: A Point Cloud Upsampling Network Using Transformer Fusion and GRU Correction

PU-CTG: A Point Cloud Upsampling Network Using Transformer Fusion and GRU Correction

Adaptive deep learning-based neighborhood search method for point cloud

Convolutional neural networks with hybrid weights for 3D point cloud classification

Contact Info

Product

Resources

About