mlsanityData to 7 Oct 2026

A Lightweight Graph Transformer Network for Human Mesh Reconstruction from 2D Human Pose

arXiv 2111.12696 ↗First posted 24 Nov 2021cs.CV cs.AI cs.HCcited by 21

Not on the map. Why?

Abstract (arXiv)

Existing deep learning-based human mesh reconstruction approaches have a tendency to build larger networks in order to achieve higher accuracy. Computational complexity and model size are often neglected, despite being key characteristics for practical use of human mesh reconstruction models (e.g. virtual try-on systems). In this paper, we present GTRS, a lightweight pose-based method that can reconstruct human mesh from 2D human pose. We propose a pose analysis module that uses graph transformers to exploit structured and implicit joint correlations, and a mesh regression module that combines the extracted pose feature with the mesh template to reconstruct the final human mesh. We demonstrate the efficiency and generalization of GTRS by extensive evaluations on the Human3.6M and 3DPW datasets. In particular, GTRS achieves better accuracy than the SOTA pose-based method Pose2Mesh while only using 10.2% of the parameters (Params) and 2.5% of the FLOPs on the challenging in-the-wild 3DPW dataset. Code will be publicly available.

Key facts. Cited by 21 papers in the map (data through 7 Oct 2026). Builds on 48 of its 62 references that are in the map. First posted on arXiv 24 Nov 2021.

Builds on

48 of 62 references.

References · 48

  1. 2017Attention Is All You Needcited by 59,932
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  4. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  5. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
  6. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  7. 2020End-to-End Object Detection with Transformerscited by 7,384
  8. 2018MobileNetV2: Inverted Residuals and Linear Bottleneckscited by 4,773
  9. 2017Squeeze-and-Excitation Networkscited by 4,763
  10. 2017MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applicationscited by 3,827
  11. 2016Gaussian Error Linear Units (GELUs)cited by 3,431
  12. 2020Deformable DETR: Deformable Transformers for End-to-End Object Detectioncited by 3,410
36 more
  1. 2020Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformerscited by 1,368
  2. 2019Deep High-Resolution Representation Learning for Human Pose Estimationcited by 1,339
  3. 2019AMASS: Archive of Motion Capture as Surface Shapescited by 1,208
  4. 2017End-to-end Recovery of Human Shape and Posecited by 883
  5. 2016Keep it SMPL: Automatic Estimation of 3D Human Pose and Shape from a Single Imagecited by 692
  6. 2018Pixel2Mesh: Generating 3D Mesh Models from Single RGB Imagescited by 649
  7. 2019Learning to Reconstruct 3D Human Pose and Shape via Model-fitting in the Loopcited by 625
  8. 2019VIBE: Video Inference for Human Body Pose and Shape Estimationcited by 615
  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. 20183D human pose estimation in video with temporal convolutions and semi-supervised trainingcited by 401
  12. 2016RMPE: Regional Multi-person Pose Estimationcited by 340
  13. 2020I2L-MeshNet: Image-to-Lixel Prediction Network for Accurate 3D Human Pose and Mesh Estimation from a Single RGB Imagecited by 274
  14. 20213D Human Pose Estimation with Spatial and Temporal Transformerscited by 271
  15. 2019Convolutional Mesh Regression for Single-Image Human Shape Reconstructioncited by 270
  16. 2021Mesh Graphormercited by 264
  17. 2017Integral Human Pose Regressioncited by 255
  18. 2021PyMAF: 3D Human Pose and Shape Regression with Pyramidal Mesh Alignment Feedback Loopcited by 250
  19. 2020Pose2Mesh: Graph Convolutional Network for 3D Human Pose and Mesh Recovery from a 2D Human Posecited by 248
  20. 2018Learning to Estimate 3D Human Pose and Shape from a Single Color Imagecited by 226
  21. 2018CrowdPose: Efficient Crowded Scenes Pose Estimation and A New Benchmarkcited by 214
  22. 2017Unite the People: Closing the Loop Between 3D and 2D Human Representationscited by 205
  23. 2019Semantic Graph Convolutional Networks for 3D Human Pose Regressioncited by 204
  24. 2017Single-Shot Multi-Person 3D Pose Estimation From Monocular RGBcited by 195
  25. 2020STAR: Sparse Trained Articulated Human Body Regressorcited by 194
  26. 2018Neural Body Fitting: Unifying Deep Learning and Model-Based Human Pose and Shape Estimationcited by 185
  27. 2019Distribution-Aware Coordinate Representation for Human Pose Estimationcited by 165
  28. 2020Beyond Static Features for Temporally Consistent 3D Human Pose and Shape from a Videocited by 162
  29. 2020Coherent Reconstruction of Multiple Humans from a Single Imagecited by 136
  30. 2021Lite-HRNet: A Lightweight High-Resolution Networkcited by 91
  31. 2019Detailed Human Shape Estimation from a Single Image by Hierarchical Mesh Deformationcited by 71
  32. 2018Real-time 2D Multi-Person Pose Estimation on CPU: Lightweight OpenPosecited by 42
  33. 2021Learning to Regress Bodies from Images using Differentiable Semantic Renderingcited by 39
  34. 20203D Human Shape and Pose from a Single Low-Resolution Image with Self-Supervised Learningcited by 28
  35. 2021GraFormer: Graph Convolution Transformer for 3D Pose Estimationcited by 10
  36. 2021Towards Fast and Accurate Multi-Person Pose Estimation on Mobile Devicescited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 5; 2023: 7; 2024: 4; 2025: 2; 2026: 3.

21 papers.

Sort:

By area:

  1. 2022A Survey on Graph Neural Networks and Graph Transformers in Computer Vision: A Task-Oriented Perspectivecited by 56
  2. 2023POTTER: Pooling Attention Transformer for Efficient Human Mesh Recoverycited by 31
  3. 2022DeciWatch: A Simple Baseline for 10x Efficient 2D and 3D Pose Estimationcited by 29
  4. 2022SkeletonMAE: Spatial-Temporal Masked Autoencoders for Self-supervised Skeleton Action Recognitioncited by 29
  5. 2023Distribution-Aligned Diffusion for Human Mesh Recoverycited by 27
  6. 2023Co-Evolution of Pose and Mesh for 3D Human Body Estimation from Videocited by 25
  7. 2023Part Aware Contrastive Learning for Self-Supervised Action Recognitioncited by 21
  8. 2025A Survey of Graph Transformers: Architectures, Theories and Applicationscited by 12
  9. 2022FeatER: An Efficient Network for Human Reconstruction via Feature Map-Based TransformERcited by 9
  10. 2023GATOR: Graph-Aware Transformer with Motion-Disentangled Regression for Human Mesh Recovery from a 2D Posecited by 4
  11. 2024ARTS: Semi-Analytical Regressor using Disentangled Skeletal Representations for Human Mesh Recovery from Videoscited by 4
  12. 2022MUG: Multi-human Graph Network for 3D Mesh Reconstruction from 2D Posecited by 3
9 more
  1. 2023Interweaved Graph and Attention Network for 3D Human Pose Estimationcited by 2
  2. 2024SkelFormer: Markerless 3D Pose and Shape Estimation using Skeletal Transformerscited by 2
  3. 2024Manufacturing Service Capability Prediction with Graph Neural Networkscited by 1
  4. 2024Dual-Branch Graph Transformer Network for 3D Human Mesh Reconstruction from Videocited by 1
  5. 2026SPRig: Self-Supervised Pose-Invariant Rigging from Mesh Sequencescited by 1
  6. 2023A Modular Multi-stage Lightweight Graph Transformer Network for Human Pose and Shape Estimation from 2D Human Posecited by 0
  7. 20253D Human Pose and Shape Estimation from LiDAR Point Clouds: A Reviewcited by 0
  8. 2026Towards Geometry-Aware and Motion-Guided Video Human Mesh Recoverycited by 0
  9. 2026MoPO: Incorporating Motion Prior for Occluded Human Mesh Recoverycited by 0