mlsanityData to 14 Oct 2026

GraFormer: Graph Convolution Transformer for 3D Pose Estimation

arXiv 2109.08364 ↗First posted 17 Sep 2021cs.CVcited by 10

Not on the map. Why?

Abstract (arXiv)

Exploiting relations among 2D joints plays a crucial role yet remains semi-developed in 2D-to-3D pose estimation. To alleviate this issue, we propose GraFormer, a novel transformer architecture combined with graph convolution for 3D pose estimation. The proposed GraFormer comprises two repeatedly stacked core modules, GraAttention and ChebGConv block. GraAttention enables all 2D joints to interact in global receptive field without weakening the graph structure information of joints, which introduces vital features for later modules. Unlike vanilla graph convolutions that only model the apparent relationship of joints, ChebGConv block enables 2D joints to interact in the high-order sphere, which formulates their hidden implicit relations. We empirically show the superiority of GraFormer through conducting extensive experiments across popular benchmarks. Specifically, GraFormer outperforms state of the art on Human3.6M dataset while using 18% parameters. The code is available at https://github.com/Graformer/GraFormer .

Key facts. Cited by 10 papers in the map (data through 14 Oct 2026). Builds on 32 of its 43 references that are in the map. First posted on arXiv 17 Sep 2021.

Builds on

32 of 43 references.

References · 32

  1. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  2. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
  3. 2017Graph Attention Networkscited by 8,923
  4. 2017Squeeze-and-Excitation Networkscited by 4,789
  5. 2015ShapeNet: An Information-Rich 3D Model Repositorycited by 2,897
  6. 2017Non-local Neural Networkscited by 2,293
  7. 2016Convolutional Neural Networks on Graphs with Fast Localized Spectral Filteringcited by 2,089
  8. 2016YOLO9000: Better, Faster, Strongercited by 1,431
  9. 2016Stacked Hourglass Networks for Human Pose Estimationcited by 915
  10. 2016Monocular 3D Human Pose Estimation In The Wild Using Improved CNN Supervisioncited by 494
  11. 2020End-to-End Human Pose and Mesh Reconstruction with Transformerscited by 418
  12. 2017A simple yet effective baseline for 3d human pose estimationcited by 401
20 more
  1. 2019Learning joint reconstruction of hands and manipulated objectscited by 378
  2. 2018Graph R-CNN for Scene Graph Generationcited by 298
  3. 2017Hand Keypoint Detection in Single Images using Multiview Bootstrappingcited by 231
  4. 2017First-Person Hand Action Benchmark with RGB-D Videos and 3D Hand Pose Annotationscited by 230
  5. 2019Actional-Structural Graph Convolutional Networks for Skeleton-based Action Recognitioncited by 228
  6. 2016Coarse-to-Fine Volumetric Prediction for Single-Image 3D Human Posecited by 221
  7. 2019Semantic Graph Convolutional Networks for 3D Human Pose Regressioncited by 204
  8. 20193D Hand Shape and Pose Estimation from a Single RGB Imagecited by 174
  9. 2017GANerated Hands for Real-time 3D Hand Tracking from Monocular RGBcited by 147
  10. 2019H+O: Unified Egocentric Recognition of 3D Hand-Object Poses and Interactionscited by 141
  11. 2017Compositional Human Pose Regressioncited by 124
  12. 2017Towards 3D Human Pose Estimation in the Wild: a Weakly-supervised Approachcited by 115
  13. 20163D Human Pose Estimation = 2D Pose Estimation + Matchingcited by 113
  14. 2020HOPE-Net: A Graph-based Model for Hand-Object Pose Estimationcited by 112
  15. 2021Skeleton Aware Multi-modal Sign Language Recognitioncited by 101
  16. 2021Graph Stacked Hourglass Networks for 3D Human Pose Estimationcited by 95
  17. 2017Exploiting temporal information for 3D pose estimationcited by 89
  18. 2016Deep Kinematic Pose Regressioncited by 40
  19. 2015Direct Prediction of 3D Body Poses from Motion Compensated Sequencescited by 26
  20. 2020Exploiting Learnable Joint Groups for Hand Pose Estimationcited by 11

Built on by

Cited by year

Citing papers per year: 2021: 1; 2022: 2; 2023: 4; 2024: 1; 2025: 2.

10 papers.

  1. 2023POTTER: Pooling Attention Transformer for Efficient Human Mesh Recoverycited by 31
  2. 2021A Lightweight Graph Transformer Network for Human Mesh Reconstruction from 2D Human Posecited by 21
  3. 20223D Vision with Transformers: A Surveycited by 21
  4. 2023Regular Splitting Graph Network for 3D Human Pose Estimationcited by 11
  5. 2022Accurate Scoliosis Vertebral Landmark Localization on X-ray Images via Shape-constrained Multi-stage Cascaded CNNscited by 3
  6. 2024STGFormer: Spatio-Temporal GraphFormer for 3D Human Pose Estimation in Videocited by 3
  7. 2025Scaling Natural-Language Graph-Based Test Time Compute for Automated Theorem Provingcited by 2
  8. 2023XFormer: Fast and Accurate Monocular 3D Body Capturecited by 1
  9. 2023Refined Temporal Pyramidal Compression-and-Amplification Transformer for 3D Human Pose Estimationcited by 0
  10. 2025Dual-stream Transformer-GCN Model with Contextualized Representations Learning for Monocular 3D Human Pose Estimationcited by 0