mlsanityData to 7 Oct 2026

PCFEx: Point Cloud Feature Extraction for Graph Neural Networks

arXiv 2603.08540 ↗First posted 9 Mar 2026cs.CV cs.IRcited by 0

Not on the map. Why?

Abstract (arXiv)

Graph neural networks (GNNs) have gained significant attention for their effectiveness across various domains. This study focuses on applying GNN to process 3D point cloud data for human pose estimation (HPE) and human activity recognition (HAR). We propose novel point cloud feature extraction (PCFEx) techniques to capture meaningful information at the point, edge, and graph levels of the point cloud by considering point cloud as a graph. Moreover, we introduce a GNN architecture designed to efficiently process these features. Our approach is evaluated on four most popular publicly available millimeter wave radar datasets, three for HPE and one for HAR. The results show substantial improvements, with significantly reduced errors in all three HPE benchmarks, and an overall accuracy of 98.8% in mmWave-based HAR, outperforming the existing state of the art models. This work demonstrates the great potential of feature extraction incorporated with GNN modeling approach to enhance the precision of point cloud processing.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 26 of its 53 references that are in the map. First posted on arXiv 9 Mar 2026.

Builds on

26 of 53 references.

References · 26

  1. 2017Attention Is All You Needcited by 59,932
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  3. 2017Graph Attention Networkscited by 8,854
  4. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,223
  5. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,384
  6. 2015ShapeNet: An Information-Rich 3D Model Repositorycited by 2,880
  7. 2019Fast Graph Representation Learning with PyTorch Geometriccited by 2,414
  8. 2020Point Transformercited by 1,462
  9. 2019Deep High-Resolution Representation Learning for Visual Recognitioncited by 1,417
  10. 2018Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognitioncited by 1,199
  11. 2018OpenPose: Realtime Multi-Person 2D Pose Estimation using Part Affinity Fieldscited by 1,161
  12. 2016Realtime Multi-Person 2D Pose Estimation using Part Affinity Fieldscited by 1,061
14 more
  1. 20183D human pose estimation in video with temporal convolutions and semi-supervised trainingcited by 401
  2. 2017Integral Human Pose Regressioncited by 255
  3. 2019HigherHRNet: Scale-Aware Representation Learning for Bottom-Up Human Pose Estimationcited by 247
  4. 2022MotionBERT: A Unified Perspective on Learning Human Motion Representationscited by 188
  5. 20182D/3D Pose Estimation and Action Recognition using Multitask Deep Learningcited by 103
  6. 2017Exploiting temporal information for 3D pose estimationcited by 89
  7. 2023MM-Fi: Multi-Modal Non-Intrusive 4D Human Dataset for Versatile Wireless Sensingcited by 77
  8. 2019mm-Pose: Real-Time Human Skeletal Posture Estimation using mmWave Radars and CNNscited by 58
  9. 2022mRI: Multi-modal 3D Human Pose Estimation Dataset using mmWave, RGB-D, and Inertial Sensorscited by 37
  10. 2022HuPR: A Benchmark for Human Pose Estimation Using Millimeter Wave Radarcited by 31
  11. 2022Fast and Scalable Human Pose Estimation using mmWave Point Cloudcited by 20
  12. 2022Learnable human mesh triangulation for 3D human pose and shape estimationcited by 16
  13. 2021Tesla-Rapture: A Lightweight Gesture Recognition System from mmWave Radar Point Cloudscited by 10
  14. 2023Representation learning of vertex heatmaps for 3D human mesh reconstruction from multi-view imagescited by 4

Built on by

Not cited yet.