mlsanityData to 14 Oct 2026

Quater-GCN: Enhancing 3D Human Pose Estimation with Orientation and Semi-supervised Training

arXiv 2404.19279 ↗First posted 30 Apr 2024cs.CVcited by 2

Not on the map. Why?

Abstract (arXiv)

3D human pose estimation is a vital task in computer vision, involving the prediction of human joint positions from images or videos to reconstruct a skeleton of a human in three-dimensional space. This technology is pivotal in various fields, including animation, security, human-computer interaction, and automotive safety, where it promotes both technological progress and enhanced human well-being. The advent of deep learning significantly advances the performance of 3D pose estimation by incorporating temporal information for predicting the spatial positions of human joints. However, traditional methods often fall short as they primarily focus on the spatial coordinates of joints and overlook the orientation and rotation of the connecting bones, which are crucial for a comprehensive understanding of human pose in 3D space. To address these limitations, we introduce Quater-GCN (Q-GCN), a directed graph convolutional network tailored to enhance pose estimation by orientation. Q-GCN excels by not only capturing the spatial dependencies among node joints through their coordinates but also integrating the dynamic context of bone rotations in 2D space. This approach enables a more sophisticated representation of human poses by also regressing the orientation of each bone in 3D space, moving beyond mere coordinate prediction. Furthermore, we complement our model with a semi-supervised training strategy that leverages unlabeled data, addressing the challenge of limited orientation ground truth data. Through comprehensive evaluations, Q-GCN has demonstrated outstanding performance against current state-of-the-art methods.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 40 of its 55 references that are in the map. First posted on arXiv 30 Apr 2024.

Builds on

40 of 55 references.

References · 40

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
  3. 2017Mask R-CNNcited by 7,277
  4. 2017Squeeze-and-Excitation Networkscited by 4,789
  5. 2019Expressive Body Capture: 3D Hands, Face, and Body from a Single Imagecited by 1,612
  6. 2018Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognitioncited by 1,209
  7. 20183D human pose estimation in video with temporal convolutions and semi-supervised trainingcited by 403
  8. 2017A simple yet effective baseline for 3d human pose estimationcited by 401
  9. 2017Learning from Synthetic Humanscited by 359
  10. 2017Cascaded Pyramid Network for Multi-Person Pose Estimationcited by 341
  11. 2020I2L-MeshNet: Image-to-Lixel Prediction Network for Accurate 3D Human Pose and Mesh Estimation from a Single RGB Imagecited by 274
  12. 20213D Human Pose Estimation with Spatial and Temporal Transformerscited by 272
28 more
  1. 2019Semantic Graph Convolutional Networks for 3D Human Pose Regressioncited by 204
  2. 2020STAR: Sparse Trained Articulated Human Body Regressorcited by 194
  3. 2022MixSTE: Seq2seq Mixed Spatio-Temporal Encoder for 3D Human Pose Estimation in Videocited by 159
  4. 2018Adaptive Graph Convolutional Neural Networkscited by 155
  5. 2021MHFormer: Multi-Hypothesis Transformer for 3D Human Pose Estimationcited by 151
  6. 2018QuaterNet: A Quaternion-based Recurrent Model for Human Motioncited by 109
  7. 2018Ordinal Depth Supervision for 3D Human Pose Estimationcited by 107
  8. 2021Graph Stacked Hourglass Networks for 3D Human Pose Estimationcited by 95
  9. 2020SRNet: Improving Generalization in 3D Human Pose Estimation with a Split-and-Recombine Approachcited by 94
  10. 2021Exploiting Temporal Contexts with Strided Transformer for 3D Human Pose Estimationcited by 94
  11. 20183D Human Pose Estimation in the Wild by Adversarial Learningcited by 86
  12. 2020Motion Guided 3D Pose Estimation from Videoscited by 85
  13. 2021Probabilistic Monocular 3D Human Pose Estimation with Normalizing Flowscited by 85
  14. 2022P-STMO: Pre-Trained Spatial Temporal Many-to-One Model for 3D Human Pose Estimationcited by 80
  15. 2020CanonPose: Self-Supervised Monocular 3D Human Pose Estimation in the Wildcited by 65
  16. 2021Conditional Directed Graph Convolution for 3D Human Pose Estimationcited by 52
  17. 2023GLA-GCN: Global-local Adaptive Graph Convolutional Network for 3D Human Pose Estimation from Monocular Videocited by 47
  18. 2018Can 3D Pose be Learned from 2D Projections Alone?cited by 44
  19. 2021Context Modeling in 3D Human Pose Estimation: A Unified Perspectivecited by 37
  20. 2018OriNet: A Fully Convolutional Network for 3D Human Pose Estimationcited by 28
  21. 2017Adversarial Inverse Graphics Networks: Learning 2D-to-3D Lifting and Image-to-Image Translation from Unpaired Supervisioncited by 27
  22. 2022H3WB: Human3.6M 3D WholeBody Dataset and Benchmarkcited by 23
  23. 2021Improving Robustness and Accuracy via Relative Information Encoding in 3D Human Pose Estimationcited by 18
  24. 2020HEMlets PoSh: Learning Part-Centric Heatmap Triplets for 3D Human Pose and Shape Estimationcited by 12
  25. 2022Jointformer: Single-Frame Lifting Transformer with Error Prediction and Refinement for 3D Human Pose Estimationcited by 10
  26. 2022PedRecNet: Multi-task deep neural network for full 3D human pose and orientation estimationcited by 4
  27. 2020Orientation Keypoints for 6D Human Pose Estimationcited by 3
  28. 2021PONet: Robust 3D Human Pose Estimation via Learning Orientations Onlycited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 1; 2025: 0; 2026: 1.

2 papers.

  1. 2024GTA-Net: An IoT-Integrated 3D Human Pose Estimation System for Real-Time Adolescent Sports Posture Correctioncited by 5
  2. 2026Amortized Inverse Kinematics via Graph Attention for Real-Time Human Avatar Animationcited by 0