mlsanityData to 7 Oct 2026

3D Human Pose Estimation Using M"obius Graph Convolutional Networks

arXiv 2203.10554 ↗First posted 20 Mar 2022cs.CVcited by 6

Not on the map. Why?

Abstract (arXiv)

3D human pose estimation is fundamental to understanding human behavior. Recently, promising results have been achieved by graph convolutional networks (GCNs), which achieve state-of-the-art performance and provide rather light-weight architectures. However, a major limitation of GCNs is their inability to encode all the transformations between joints explicitly. To address this issue, we propose a novel spectral GCN using the M"obius transformation (M"obiusGCN). In particular, this allows us to directly and explicitly encode the transformation between joints, resulting in a significantly more compact representation. Compared to even the lightest architectures so far, our novel approach requires 90-98% fewer parameters, i.e. our lightest M"obiusGCN uses only 0.042M trainable parameters. Besides the drastic parameter reduction, explicitly encoding the transformation of joints also enables us to achieve state-of-the-art results. We evaluate our approach on the two challenging pose estimation benchmarks, Human3.6M and MPI-INF-3DHP, demonstrating both state-of-the-art results and the generalization capabilities of M"obiusGCN.

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Builds on 51 of its 74 references that are in the map. First posted on arXiv 20 Mar 2022.

Builds on

51 of 74 references.

References · 51

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  3. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  4. 2017Graph Attention Networkscited by 8,854
  5. 2017Inductive Representation Learning on Large Graphscited by 6,284
  6. 2017Neural Message Passing for Quantum Chemistrycited by 3,460
  7. 2016Convolutional Neural Networks on Graphs with Fast Localized Spectral Filteringcited by 2,085
  8. 2018Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognitioncited by 1,199
  9. 2018On the Continuity of Rotation Representations in Neural Networkscited by 1,186
  10. 2013Spectral Networks and Locally Connected Networks on Graphscited by 1,097
  11. 2016Geometric deep learning: going beyond Euclidean datacited by 1,042
  12. 2016Stacked Hourglass Networks for Human Pose Estimationcited by 913
38 more
  1. 2016Monocular 3D Human Pose Estimation In The Wild Using Improved CNN Supervisioncited by 493
  2. 2017A simple yet effective baseline for 3d human pose estimationcited by 401
  3. 20183D human pose estimation in video with temporal convolutions and semi-supervised trainingcited by 401
  4. 2018Hyperbolic Neural Networkscited by 393
  5. 2017Cascaded Pyramid Network for Multi-Person Pose Estimationcited by 341
  6. 2017VITON: An Image-based Virtual Try-on Networkcited by 285
  7. 2015Deep Convolutional Networks on Graph-Structured Datacited by 246
  8. 2016Coarse-to-Fine Volumetric Prediction for Single-Image 3D Human Posecited by 220
  9. 2017Deep Complex Networkscited by 215
  10. 2019Semantic Graph Convolutional Networks for 3D Human Pose Regressioncited by 204
  11. 2017CayleyNets: Graph Convolutional Neural Networks with Complex Rational Spectral Filterscited by 203
  12. 2019Graph Neural Networks with convolutional ARMA filterscited by 185
  13. 2017Compositional Human Pose Regressioncited by 124
  14. 2017Towards 3D Human Pose Estimation in the Wild: a Weakly-supervised Approachcited by 114
  15. 2018Ordinal Depth Supervision for 3D Human Pose Estimationcited by 107
  16. 20182D/3D Pose Estimation and Action Recognition using Multitask Deep Learningcited by 103
  17. 2021Graph Stacked Hourglass Networks for 3D Human Pose Estimationcited by 94
  18. 2019Generating Multiple Hypotheses for 3D Human Pose Estimation with Mixture Density Networkcited by 92
  19. 2017Exploiting temporal information for 3D pose estimationcited by 89
  20. 20183D Human Pose Estimation in the Wild by Adversarial Learningcited by 86
  21. 2019Monocular 3D Human Pose Estimation by Generation and Ordinal Rankingcited by 76
  22. 2018Learning Monocular 3D Human Pose Estimation from Multi-view Imagescited by 70
  23. 2020Weakly-Supervised 3D Human Pose Learning via Multi-view Images in the Wildcited by 66
  24. 2020CanonPose: Self-Supervised Monocular 3D Human Pose Estimation in the Wildcited by 65
  25. 2019TexturePose: Supervising Human Mesh Estimation with Texture Consistencycited by 53
  26. 2019HEMlets Pose: Learning Part-Centric Heatmap Triplets for Accurate 3D Human Pose Estimationcited by 50
  27. 2018Jointly Optimize Data Augmentation and Network Training: Adversarial Data Augmentation in Human Pose Estimationcited by 44
  28. 2016Deep Kinematic Pose Regressioncited by 40
  29. 2020AdaFuse: Adaptive Multiview Fusion for Accurate Human Pose Estimation in the Wildcited by 40
  30. 2021Context Modeling in 3D Human Pose Estimation: A Unified Perspectivecited by 37
  31. 2017MonoCap: Monocular Human Motion Capture using a CNN Coupled with a Geometric Priorcited by 36
  32. 2020MeTRAbs: Metric-Scale Truncation-Robust Heatmaps for Absolute 3D Human Pose Estimationcited by 35
  33. 2019Multiview-Consistent Semi-Supervised Learning for 3D Human Pose Estimationcited by 31
  34. 2017Adversarial Inverse Graphics Networks: Learning 2D-to-3D Lifting and Image-to-Image Translation from Unpaired Supervisioncited by 27
  35. 2018Soccer on Your Tabletopcited by 20
  36. 20205* Knowledge Graph Embeddings with Projective Transformationscited by 19
  37. 2018Complex Gated Recurrent Neural Networkscited by 17
  38. 2020Data augmentation with Mobius transformationscited by 9

50 most cited of 51 All 51 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 1; 2023: 1; 2024: 2; 2025: 1; 2026: 1.

6 papers.

  1. 2023OmniZoomer: Learning to Move and Zoom in on Sphere at High-Resolutioncited by 7
  2. 2024Expanding Expressivity in Transformer Models with M"obiusAttentioncited by 4
  3. 2024M"obius Transform for Mitigating Perspective Distortions in Representation Learningcited by 2
  4. 2022A New Spatio-Temporal Loss Function for 3D Motion Reconstruction and Extended Temporal Metrics for Motion Evaluationcited by 1
  5. 2025PoseGRAF: Geometric-Reinforced Adaptive Fusion for Monocular 3D Human Pose Estimationcited by 0
  6. 2026HYPERPOSE: Hyperbolic Kinematic Phase-Space Attention for 3D Human Pose Estimationcited by 0