mlsanityData to 7 Oct 2026

Iterative Graph Filtering Network for 3D Human Pose Estimation

arXiv 2307.16074 ↗First posted 29 Jul 2023cs.CVcited by 1

Not on the map. Why?

Abstract (arXiv)

Graph convolutional networks (GCNs) have proven to be an effective approach for 3D human pose estimation. By naturally modeling the skeleton structure of the human body as a graph, GCNs are able to capture the spatial relationships between joints and learn an efficient representation of the underlying pose. However, most GCN-based methods use a shared weight matrix, making it challenging to accurately capture the different and complex relationships between joints. In this paper, we introduce an iterative graph filtering framework for 3D human pose estimation, which aims to predict the 3D joint positions given a set of 2D joint locations in images. Our approach builds upon the idea of iteratively solving graph filtering with Laplacian regularization via the Gauss-Seidel iterative method. Motivated by this iterative solution, we design a Gauss-Seidel network (GS-Net) architecture, which makes use of weight and adjacency modulation, skip connection, and a pure convolutional block with layer normalization. Adjacency modulation facilitates the learning of edges that go beyond the inherent connections of body joints, resulting in an adjusted graph structure that reflects the human skeleton, while skip connections help maintain crucial information from the input layer's initial features as the network depth increases. We evaluate our proposed model on two standard benchmark datasets, and compare it with a comprehensive set of strong baseline methods for 3D human pose estimation. Our experimental results demonstrate that our approach outperforms the baseline methods on both datasets, achieving state-of-the-art performance. Furthermore, we conduct ablation studies to analyze the contributions of different components of our model architecture and show that the skip connection and adjacency modulation help improve the model performance.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 48 of its 73 references that are in the map. First posted on arXiv 29 Jul 2023.

Builds on

48 of 73 references.

References · 48

  1. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
  2. 2022A ConvNet for the 2020scited by 3,545
  3. 2020Deformable DETR: Deformable Transformers for End-to-End Object Detectioncited by 3,410
  4. 2017Non-local Neural Networkscited by 2,290
  5. 2019Deep High-Resolution Representation Learning for Human Pose Estimationcited by 1,339
  6. 2018Predict then Propagate: Graph Neural Networks meet Personalized PageRankcited by 987
  7. 2018Representation Learning on Graphs with Jumping Knowledge Networkscited by 875
  8. 2020Simple and Deep Graph Convolutional Networkscited by 857
  9. 2016Monocular 3D Human Pose Estimation In The Wild Using Improved CNN Supervisioncited by 493
  10. 2020End-to-End Human Pose and Mesh Reconstruction with Transformerscited by 417
  11. 2017A simple yet effective baseline for 3d human pose estimationcited by 401
  12. 20183D human pose estimation in video with temporal convolutions and semi-supervised trainingcited by 401
36 more
  1. 2017Cascaded Pyramid Network for Multi-Person Pose Estimationcited by 341
  2. 2013DeepPose: Human Pose Estimation via Deep Neural Networkscited by 305
  3. 20213D Human Pose Estimation with Spatial and Temporal Transformerscited by 271
  4. 2017Integral Human Pose Regressioncited by 255
  5. 2020Pose2Mesh: Graph Convolutional Network for 3D Human Pose and Mesh Recovery from a 2D Human Posecited by 248
  6. 2016Coarse-to-Fine Volumetric Prediction for Single-Image 3D Human Posecited by 220
  7. 2019Semantic Graph Convolutional Networks for 3D Human Pose Regressioncited by 204
  8. 2020Scaling Graph Neural Networks with Approximate PageRankcited by 174
  9. 2017Compositional Human Pose Regressioncited by 124
  10. 2020Epipolar Transformerscited by 117
  11. 2017Towards 3D Human Pose Estimation in the Wild: a Weakly-supervised Approachcited by 114
  12. 20163D Human Pose Estimation = 2D Pose Estimation + Matchingcited by 112
  13. 2018Ordinal Depth Supervision for 3D Human Pose Estimationcited by 107
  14. 2020SRNet: Improving Generalization in 3D Human Pose Estimation with a Split-and-Recombine Approachcited by 94
  15. 2021Graph Stacked Hourglass Networks for 3D Human Pose Estimationcited by 94
  16. 2019Generating Multiple Hypotheses for 3D Human Pose Estimation with Mixture Density Networkcited by 92
  17. 2019Cross View Fusion for 3D Human Pose Estimationcited by 90
  18. 2017Exploiting temporal information for 3D pose estimationcited by 89
  19. 2019Human Mesh Recovery from Monocular Images via a Skeleton-disentangled Representationcited by 87
  20. 20183D Human Pose Estimation in the Wild by Adversarial Learningcited by 86
  21. 2020Motion Guided 3D Pose Estimation from Videoscited by 85
  22. 2019Monocular 3D Human Pose Estimation by Generation and Ordinal Rankingcited by 76
  23. 2017Lifting from the Deep: Convolutional 3D Pose Estimation from a Single Imagecited by 73
  24. 2021Learning Skeletal Graph Neural Networks for Hard 3D Pose Estimationcited by 62
  25. 2021Deep Dual Consecutive Network for Human Pose Estimationcited by 51
  26. 2019HEMlets Pose: Learning Part-Centric Heatmap Triplets for Accurate 3D Human Pose Estimationcited by 50
  27. 2021Recent Advances in Monocular 2D and 3D Human Pose Estimation: A Deep Learning Perspectivecited by 49
  28. 2019In the Wild Human Pose Estimation Using Explicit 2D Features and Intermediate 3D Representationscited by 48
  29. 2016Deep Kinematic Pose Regressioncited by 40
  30. 2021Bag of Tricks for Training Deeper Graph Neural Networks: A Comprehensive Benchmark Studycited by 36
  31. 20163D Human Pose Estimation Using Convolutional Neural Networks with 2D Pose Informationcited by 28
  32. 2020Weakly Supervised Generative Network for Multiple 3D Human Pose Hypothesescited by 25
  33. 2022Temporal Feature Alignment and Mutual Information Maximization for Video-Based Human Pose Estimationcited by 24
  34. 2019Not All Parts Are Created Equal: 3D Pose Estimation by Modelling Bi-directional Dependencies of Body Partscited by 19
  35. 20213D Human Pose Regression using Graph Convolutional Networkcited by 8
  36. 2021Higher-Order Implicit Fairing Networks for 3D Human Pose Estimationcited by 8

Built on by

Cited by year

Citing papers per year: 2024: 1.

1 paper.

  1. 2024Multi-hop graph transformer network for 3D human pose estimationcited by 1