High-resolution Feature Network for 3D Point Cloud Segmentation and Classification

Zhu Junjie; Liu Dongfeng

doi:10.12052/gdutxb.240083

English Version Journal Login

您当前的位置：

首页 >

文章列表页 >

High-resolution Feature Network for 3D Point Cloud Segmentation and Classification

更新时间：2026-05-27

- High-resolution Feature Network for 3D Point Cloud Segmentation and Classification
- Vol. 42, Issue 3, Pages: 44-51(2025)
- 作者机构：
  
  广东工业大学信息工程学院,广东,广州,510006
- 作者简介：
- 基金信息：
- DOI：10.12052/gdutxb.240083
  CLC： TP391.4;TP181
- Published：2025
- 稿件说明：
移动端阅览
朱骏杰, 刘东峰. 用于三维点云分割和分类的高分辨率特征网络[J]. 广东工业大学学报, 2025, 42(3): 44–51.

Zhu Junjie, Liu Dongfeng. High-resolution Feature Network for 3D Point Cloud Segmentation and Classification[J]. 2025, 42(3): 44-51.
朱骏杰, 刘东峰. 用于三维点云分割和分类的高分辨率特征网络[J]. 广东工业大学学报, 2025, 42(3): 44–51. DOI： 10.12052/gdutxb.240083

Zhu Junjie, Liu Dongfeng. High-resolution Feature Network for 3D Point Cloud Segmentation and Classification[J]. 2025, 42(3): 44-51. DOI： 10.12052/gdutxb.240083.

摘要

多尺度特征在点云领域的密集预测任务中至关重要。当前三维点云处理技术主要依赖编码器−解码器框架，通过主干网络提取并融合多尺度特征。然而，这些方法通常采用延迟融合策略，导致特征集成不足。为解决这一问题，本文提出了HRFN3D(High-resolution Feature Network for 3D Point Cloud)模型，一种专为点云分类和分割任务设计的高分辨率特征网络。HRFN3D通过创新性的关系学习模块，在早期阶段进行特征融合，促进低分辨率高语义点与高分辨率低语义点的交互，使高分辨率点在早期阶段就保留高语义信息，优化后续特征学习。在后期，结合不同池化策略生成全局特征向量，并与原始点特征拼接，既保留细节，又增强全局特征的代表性。实验结果显示，HRFN3D在ShapeNetPart数据集上将类平均交并比和实例平均交并比分别提升了2.2个百分点和0.9个百分点，并获得了最佳实例平均交并比86.3%；在ModelNet40数据集上，以4.3 M的参数量实现了91.5%的最高类平均精度。这些结果验证了HRFN3D在多尺度特征处理中的有效性。

Abstract

Multi-scale features are critical in dense prediction tasks within the point cloud domain. Existing 3D point cloud processing techniques predominantly rely on encoder-decoder frameworks

which extract and integrate multiscale features via a backbone network. However

these methods often employ delayed fusion strategies

resulting in insufficient feature integration. To address this issue

this paper introduces a novel high-resolution feature network for 3D point cloud

named HRFN3D

specifically for point cloud classification and segmentation tasks. HRFN3D innovatively employs a relational learning module to perform feature fusion at an early stage

facilitating interactions between low-resolution high-semantic points and high-resolution low-semantic points. This early fusion ensures that high-resolution points retain semantic information from the outset

facilitating subsequent feature learning. In the later stage

the global feature vectors are generated by combining different pooling strategies and spliced with the original point features

preserving the details and enhancing the representation of the global features. The experimental results show that HRFN3D improves the Class mean and Instance mean Intersection over Union by 2.2 percentage point and 0.9 percentage point

respectively

and achieves the average class ratio of 86.3%. On the ModelNet40 data set

our proposed method achieves the highest class average accuracy of 91.5% with 4.3M parameters. These results validate the effectiveness of HRFN3D in multi-scale feature processing.

关键词

Keywords

references

ALEXIOU E, YANG N, EBRAHIMI T. PointXR: a toolbox for visualization and subjective evaluation of point clouds in virtual reality[C]//2020 Twelfth International Conference on Quality of Multimedia Experience (QoMEX) . Athlone: IEEE, 2020: 1-6.

CHEN Y Q, WANG Q, CHEN H, et al . An overview of augmented reality technology[J ] . Journal of Physics: Conference Series, 2019, 1237(2): 022082.

AKSOY E E, BACI S, CAVDAR S. Salsanet: fast road and vehicle segmentation in lidar point clouds for autonomous driving[C]//2020 IEEE Intelligent Vehicles Symposium (IV) . Las Vegas: IEEE, 2020: 926-932.

LI Y, MA L, ZHONG Z, et al . Deep learning for lidar point clouds in autonomous driving: a review[J ] . IEEE Transactions on Neural Networks and Learning Systems, 2020, 32(8): 3412-3432.

LI X, DU S, LI G, et al . Integrate point-cloud segmentation with 3D LiDAR scan-matching for mobile robot localization and mapping[J ] . Sensors, 2019, 20(1): 237.

YANG L, LIU Y, PENG J, et al . A novel system for off-line 3D seam extraction and path planning based on point cloud segmentation for arc welding robot[J ] . Robotics and Computer-Integrated Manufacturing, 2020, 64: 101929.

GUO Y, WANG H, HU Q, et al . Deep learning for 3D point clouds: a survey[J ] . IEEE Transactions on Pattern Analysis and Machine Intelligence, 2020, 43(12): 4338-4364.

LUO C, YANG X, YUILLE A. Exploring simple 3D multi-object tracking for autonomous driving[C]//Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) . Montreal: IEEE, 2021: 10488-10497.

ZHAO L, CAI D, SHENG L, et al . 3DVG-Transformer: relation modeling for visual grounding on point clouds[C ] //Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV). Montreal: IEEE, 2021: 2928-2937.

QI C, SU H, MO K, et al . PointNet: deep learning on point sets for 3D classification and segmentation[C ] //Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) . Honolulu: IEEE, 2017: 652-660.

QI C, SU H, MO K, et al . PointNet++: deep hierarchical feature learning on point sets in a metric space[J ] . Advances in Neural Information Processing Systems, 2017, 30: 5105-5114.

LI Y, BU R, SUN M, et al . PointCNN: convolution on x-transformed points[J ] . Advances in Neural Information Processing Systems, 2018, 31: 828-838.

YAN X, ZHENG C, LI Z, et al . PointASNL: robust point clouds processing using nonlocal neural networks with adaptive sampling[C ] //Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) . Seattle: IEEE, 2020: 5589-5598.

WU W, QI Z, FUXIN L. PointConv: deep convolutional networks on 3D point clouds[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) . Long Beach: IEEE, 2019: 9621-9630.

QIAN G, LI Y, PENG H, et al . PointNeXt: revisiting pointnet++ with improved training and scaling strategies[J ] . Advances in Neural Information Processing Systems, 2022, 35: 23192-23204.

ZHAO H, JIANG L, JIA J, et al . Point transformer[C ] //Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) . Montreal: IEEE, 2021: 16259-16268.

SUN K, XIAO B, LIU D, et al . Deep high-resolution representation learning for human pose estimation[C ] //Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recogniti on (CVPR) . Long Beach: IEEE, 2019: 5693-5703.

WANG J, SUN K, CHENG T, et al . Deep high-resolution representation learning for visual recognition[J ] . IEEE Transactions on Pattern Analysis and Machine Intelligence, 2020, 43(10): 3349-3364.

VASWANI A, SHAZEER N, PARMAR N, et al . Attention is all you need[J ] . Advances in Neural Information Processing Systems, 2017, 30: 6000-6010.

ZHANG G, GE Y, DONG Z, et al . Deep high-resolution representation learning for cross-resolution person re-identification[J ] . IEEE Transactions on Image Processing, 2021, 30: 8913-8925.

WU X, LAO Y, JIANG L, et al . Point transformer v2: grouped vector attention and partition-based pooling[J ] . Advances in Neural Information Processing Systems, 2022, 35: 33330-33342.

GUO M, CAI J, LIU Z, et al . PCT: point cloud transformer[J ] . Computational Visual Media, 2021, 7: 187-199.

THOMAS H, QI C, DESCHAUD J, et al . KPConv: flexible and deformable convolution for point clouds[C ] //Proceedings of the IEEE/CVF International Conference on Computer Vis ion (ICCV) . Seoul: IEEEE, 2019: 6411-6420.

WANG Y, SUN Y, LIU Z, et al . Dynamic graph CNN for learning on point clouds[J ] . ACM Transactions on Graphics, 2019, 38(5): 1-12.

LIU X, HAN Z, LIU Y, et al . Point2sequence: learning the shape representation of 3D point clouds with an attention-based sequence to sequence network[C ] //Proceedings of the AAAI Conference on Artificial Intelligence (AAAI) . Hawaii: AAAI, 2019, 33(01): 8778-8785.

LIU Y, FAN B, XIANG S, et al . Relation-shape convolutional neural network for point cloud analysis[C ] //Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) . Long Beach: IEEE, 2019: 8895-8904.

SU H, JAMPANI V, SUN D, et al . SplatNet: sparse lattice networks for point cloud processing[C ] //Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) . Salt Lake City: IEEE, 2018: 2530-2539.

XU Y, FAN T, XU M, et al . SpiderCNN: deep learning on point sets with parameterized convolutional filters[C ] //Proceedings of the European Conference on Computer Vision (ECCV) . Munich: CVF, 2018: 87-102.

LI Z, GAO P, YUAN H, et al . Exploiting inductive bias in transformer for point cloud classification and segmentation[C ] //2023 IEEE International Conference on Multimedia and Expo Workshops (ICMEW). Brisbane: IEEE, 2023: 140-145.

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Local Orthogonal Feature Fusion for Few-Shot Image Classification

Surface Defect Detection of Lithium Battery Electrodes Based on Improved Unet Network

Super-resolution Reconstruction of Images Based on Blueprint Separable Residual Distillation Network

An Insulator Burst Defect Detection Method Based on YOLOv4-MP

A Research on Deep Learning Object Detection Algorithm Based on Feature Fusion

Related Author

Huang Guo-heng

Cheng Liang-lun

Tu Ze-liang

Liu Guo-dong

Cheng Si-yuan

Yang Xue-rong

Chen Xiao-rong

Xiong Rong-sheng

Related Institution

School of Computer Science and Technology, Guangdong University of Technology

School of Electromechanical Engineering, Guangdong University of Technology

Yunnan Electric Power Research Institute, Yunnan Power Grid Co., Ltd

School of Applied Mathematics, Guangdong University of Technology

School of Computers, Guangdong University of Technology

AI问答

⁰