mlsanityData to 7 Oct 2026

Mesh Graphormer

arXiv 2104.00272 ↗First posted 1 Apr 2021cs.CVcited by 264

Not on the map. Why?

Abstract (arXiv)

We present a graph-convolution-reinforced transformer, named Mesh Graphormer, for 3D human pose and mesh reconstruction from a single image. Recently both transformers and graph convolutional neural networks (GCNNs) have shown promising progress in human mesh reconstruction. Transformer-based approaches are effective in modeling non-local interactions among 3D mesh vertices and body joints, whereas GCNNs are good at exploiting neighborhood vertex interactions based on a pre-specified mesh topology. In this paper, we study how to combine graph convolutions and self-attentions in a transformer to model both local and global interactions. Experimental results show that our proposed method, Mesh Graphormer, significantly outperforms the previous state-of-the-art methods on multiple benchmarks, including Human3.6M, 3DPW, and FreiHAND datasets. Code and pre-trained models are available at https://github.com/microsoft/MeshGraphormer

Key facts. Cited by 264 papers in the map (data through 7 Oct 2026). Builds on 36 of its 44 references that are in the map. First posted on arXiv 1 Apr 2021.

Builds on

36 of 44 references.

References · 36

  1. 2017Attention Is All You Needcited by 59,932
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  3. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  4. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  5. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  6. 2016Layer Normalizationcited by 5,579
  7. 2016Gaussian Error Linear Units (GELUs)cited by 3,431
  8. 2020Conformer: Convolution-augmented Transformer for Speech Recognitioncited by 1,838
  9. 2018Group Normalizationcited by 1,514
  10. 2019Deep High-Resolution Representation Learning for Visual Recognitioncited by 1,417
  11. 2021Transformers in Vision: A Surveycited by 1,009
  12. 2017End-to-end Recovery of Human Shape and Posecited by 883
24 more
  1. 2020Efficient Transformers: A Surveycited by 784
  2. 2018Pixel2Mesh: Generating 3D Mesh Models from Single RGB Imagescited by 649
  3. 2019Learning to Reconstruct 3D Human Pose and Shape via Model-fitting in the Loopcited by 625
  4. 2019VIBE: Video Inference for Human Body Pose and Shape Estimationcited by 615
  5. 2018DensePose: Dense Human Pose Estimation In The Wildcited by 573
  6. 2020End-to-End Human Pose and Mesh Reconstruction with Transformerscited by 417
  7. 2020I2L-MeshNet: Image-to-Lixel Prediction Network for Accurate 3D Human Pose and Mesh Estimation from a Single RGB Imagecited by 274
  8. 2019FreiHAND: A Dataset for Markerless Capture of Hand Pose and Shape from Single RGB Imagescited by 271
  9. 2019Convolutional Mesh Regression for Single-Image Human Shape Reconstructioncited by 270
  10. 2018Generating 3D faces using Convolutional Mesh Autoencoderscited by 267
  11. 2020Pose2Mesh: Graph Convolutional Network for 3D Human Pose and Mesh Recovery from a 2D Human Posecited by 248
  12. 2018Learning to Estimate 3D Human Pose and Shape from a Single Color Imagecited by 226
  13. 2017Unite the People: Closing the Loop Between 3D and 2D Human Representationscited by 205
  14. 2017Single-Shot Multi-Person 3D Pose Estimation From Monocular RGBcited by 195
  15. 2018Neural Body Fitting: Unifying Deep Learning and Model-Based Human Pose and Shape Estimationcited by 185
  16. 2018QANet: Combining Local Convolution with Global Self-Attention for Reading Comprehensioncited by 164
  17. 2020Beyond Static Features for Temporally Consistent 3D Human Pose and Shape from a Videocited by 162
  18. 2020In Defense of Grid Features for Visual Question Answeringcited by 155
  19. 2018A2-Nets: Double Attention Networkscited by 136
  20. 2020Lite Transformer with Long-Short Range Attentioncited by 127
  21. 2017Self-supervised Learning of Motion Capturecited by 97
  22. 2020Human Mesh Recovery from Multiple Shotscited by 52
  23. 2019Learning 3D Human Shape and Pose from Dense Body Partscited by 48
  24. 2017MonoCap: Monocular Human Motion Capture using a CNN Coupled with a Geometric Priorcited by 36

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 10; 2022: 45; 2023: 80; 2024: 69; 2025: 37; 2026: 23.

264 papers.

Sort:

By area:

  1. 2023Humans in 4D: Reconstructing and Tracking Humans with Transformerscited by 344
  2. 2022HOI4D: A 4D Egocentric Dataset for Category-Level Human-Object Interactioncited by 321
  3. 2023Reconstructing Hands in 3D with Transformerscited by 298
  4. 2022CLIFF: Carrying Location Information in Full Frames into Human Pose and Shape Estimationcited by 237
  5. 2023BEDLAM: A Synthetic Dataset of Bodies Exhibiting Detailed Lifelike Animated Motioncited by 229
  6. 2022Pure Transformers are Powerful Graph Learnerscited by 188
  7. 2022MotionBERT: A Unified Perspective on Learning Human Motion Representationscited by 188
  8. 2022Capturing and Inferring Dense Full-Body Human-Scene Contactcited by 176
  9. 2023FastViT: A Fast Hybrid Vision Transformer using Structural Reparameterizationcited by 161
  10. 2022PyMAF-X: Towards Well-aligned Full-body Model Regression from Monocular Imagescited by 152
  11. 2021Keypoint Transformer: Solving Joint Identification in Challenging Hands and Object Interactions for Accurate 3D Pose Estimationcited by 122
  12. 2024WiLoR: End-to-end 3D Hand Localization and Reconstruction in-the-wildcited by 117
38 more
  1. 2022Transformer for Graphs: An Overview from Architecture Perspectivecited by 107
  2. 2024TRAM: Global Trajectory and Motion of 3D Humans from in-the-wild Videoscited by 105
  3. 2022Recovering 3D Human Mesh from Monocular Images: A Surveycited by 103
  4. 2022Not All Tokens Are Equal: Human-centric Visual Analysis via Token Clustering Transformercited by 99
  5. 2023EMDB: The Electromagnetic Database of Global 3D Human Pose and Shape in the Wildcited by 95
  6. 2024TokenHMR: Advancing Human Mesh Recovery with a Tokenized Pose Representationcited by 93
  7. 2022Interacting Attention Graph for Single Image Two-Hand Reconstructioncited by 87
  8. 2024DINO-X: A Unified Vision Model for Open-World Object Detection and Understandingcited by 85
  9. 2022Cross-Attention of Disentangled Modalities for 3D Human Mesh Recovery with Transformerscited by 81
  10. 2023Attending to Graph Transformerscited by 81
  11. 2021MobRecon: Mobile-Friendly Hand Mesh Reconstruction from Monocular Imagecited by 74
  12. 2025PromptHMR: Promptable Human Mesh Recoverycited by 70
  13. 2025HaWoR: World-Space Hand Motion Reconstruction from Egocentric Videoscited by 62
  14. 2023EgoHumans: An Egocentric 3D Multi-Human Benchmarkcited by 58
  15. 2024Neural Localizer Fields for Continuous 3D Human Pose and Shape Estimationcited by 57
  16. 2022A Survey on Graph Neural Networks and Graph Transformers in Computer Vision: A Task-Oriented Perspectivecited by 56
  17. 2022Occluded Human Mesh Recoverycited by 52
  18. 2022Learning 3D Human Pose Estimation from Dozens of Datasets using a Geometry-Aware Autoencoder to Bridge Between Skeleton Formatscited by 50
  19. 2023ReFit: Recurrent Fitting Network for 3D Human Recoverycited by 47
  20. 2023NIKI: Neural Inverse Kinematics with Invertible Neural Networks for 3D Human Pose and Shape Estimationcited by 45
  21. 2024Hamba: Single-view 3D Hand Reconstruction with Graph-guided Bi-Scanning Mambacited by 45
  22. 20233D Human Mesh Estimation from Virtual Markerscited by 44
  23. 2023HandRefiner: Refining Malformed Hands in Generated Images by Diffusion-based Conditional Inpaintingcited by 42
  24. 2022TORE: Token Reduction for Efficient Human Mesh Recovery with Transformercited by 41
  25. 2023Zolly: Zoom Focal Length Correctly for Perspective-Distorted Human Mesh Reconstructioncited by 41
  26. 2023Realistic Full-Body Tracking from Sparse Observations via Joint-Level Modelingcited by 41
  27. 2024AiOS: All-in-One-Stage Expressive Human Pose and Shape Estimationcited by 41
  28. 2024Score-Guided Diffusion for 3D Human Recoverycited by 39
  29. 2023ACR: Attention Collaboration-based Regressor for Arbitrary Two-Hand Reconstructioncited by 37
  30. 2021ElePose: Unsupervised 3D Human Pose Estimation by Predicting Camera Elevation and Learning Normalizing Flows on 2D Posescited by 35
  31. 2022Hierarchical Temporal Transformer for 3D Hand Pose Estimation and Action Recognition from Egocentric RGB Videoscited by 35
  32. 2021AdaptPose: Cross-Dataset Adaptation for 3D Human Pose Estimation by Learnable Motion Generationcited by 32
  33. 2022MeshMAE: Masked Autoencoders for 3D Mesh Data Analysiscited by 31
  34. 2023PSVT: End-to-End Multi-person 3D Pose and Shape Estimation with Progressive Video Transformerscited by 31
  35. 2023POTTER: Pooling Attention Transformer for Efficient Human Mesh Recoverycited by 31
  36. 2024Harmony4D: A Video Dataset for In-The-Wild Close Human Interactionscited by 31
  37. 2022Benchmarking and Analyzing 3D Human Pose and Shape Estimation Beyond Algorithmscited by 28
  38. 20233D-Aware Neural Body Fitting for Occlusion Robust 3D Human Pose Estimationcited by 28

50 most cited of 264 All 264 (JSON)