mlsanityData to 14 Oct 2026

3D Landmark Detection on Human Point Clouds: A Benchmark and A Dual Cascade Point Transformer Framework

arXiv 2401.07251 ↗First posted 14 Jan 2024cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

3D landmark detection plays a pivotal role in various applications such as 3D registration, pose estimation, and virtual try-on. While considerable success has been achieved in 2D human landmark detection or pose estimation, there is a notable scarcity of reported works on landmark detection in unordered 3D point clouds. This paper introduces a novel challenge, namely 3D landmark detection on human point clouds, presenting two primary contributions. Firstly, we establish a comprehensive human point cloud dataset, named HPoint103, designed to support the 3D landmark detection community. This dataset comprises 103 human point clouds created with commercial software and actors, each manually annotated with 11 stable landmarks. Secondly, we propose a Dual Cascade Point Transformer (D-CPT) model for precise point-based landmark detection. D-CPT gradually refines the landmarks through cascade Transformer decoder layers across the entire point cloud stream, simultaneously enhancing landmark coordinates with a RefineNet over local regions. Comparative evaluations with popular point-based methods on HPoint103 and the public dataset DHP19 demonstrate the dramatic outperformance of our D-CPT. Additionally, the integration of our RefineNet into existing methods consistently improves performance.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 23 of its 43 references that are in the map. First posted on arXiv 14 Jan 2024.

Builds on

23 of 43 references.

References · 23

  1. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  2. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,248
  3. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,401
  4. 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,223
  5. 2018PointPillars: Fast Encoders for Object Detection from Point Cloudscited by 1,715
  6. 2017VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detectioncited by 1,323
  7. 2016Stacked Hourglass Networks for Human Pose Estimationcited by 915
  8. 2020PCT: Point cloud transformercited by 732
  9. 2016Multi-View 3D Object Detection Network for Autonomous Drivingcited by 724
  10. 2015Multi-view Convolutional Neural Networks for 3D Shape Recognitioncited by 565
  11. 2019Stand-Alone Self-Attention in Vision Modelscited by 542
  12. 2018Simple Baselines for Human Pose Estimation and Trackingcited by 502
11 more
  1. 2016Monocular 3D Human Pose Estimation In The Wild Using Improved CNN Supervisioncited by 494
  2. 2016Semantic Scene Completion from a Single Depth Imagecited by 472
  3. 2016Convolutional Pose Machinescited by 325
  4. 2020Exploring Self-attention for Image Recognitioncited by 313
  5. 2013DeepPose: Human Pose Estimation via Deep Neural Networkscited by 305
  6. 2016Panoptic Studio: A Massively Multiview System for Social Interaction Capturecited by 173
  7. 2020Real-Time High-Resolution Background Mattingcited by 173
  8. 2015Human Pose Estimation with Iterative Error Feedbackcited by 121
  9. 2016Vehicle Detection from 3D Lidar Using Fully Convolutional Networkcited by 107
  10. 20213D Adversarial Attacks Beyond Point Cloudcited by 26
  11. 2022PCSCNet: Fast 3D Semantic Segmentation of LiDAR Point Cloud for Autonomous Car using Point Convolution and Sparse Convolution Networkcited by 14

Built on by

Not cited yet.