mlsanityData to 7 Oct 2026

GATOR: Graph-Aware Transformer with Motion-Disentangled Regression for Human Mesh Recovery from a 2D Pose

arXiv 2303.05652 ↗First posted 10 Mar 2023cs.CV cs.AI cs.LGcited by 4

Not on the map. Why?

Abstract (arXiv)

3D human mesh recovery from a 2D pose plays an important role in various applications. However, it is hard for existing methods to simultaneously capture the multiple relations during the evolution from skeleton to mesh, including joint-joint, joint-vertex and vertex-vertex relations, which often leads to implausible results. To address this issue, we propose a novel solution, called GATOR, that contains an encoder of Graph-Aware Transformer (GAT) and a decoder with Motion-Disentangled Regression (MDR) to explore these multiple relations. Specifically, GAT combines a GCN and a graph-aware self-attention in parallel to capture physical and hidden joint-joint relations. Furthermore, MDR models joint-vertex and vertex-vertex interactions to explore joint and vertex relations. Based on the clustering characteristics of vertex offset fields, MDR regresses the vertices by composing the predicted base motions. Extensive experiments show that GATOR achieves state-of-the-art performance on two challenging benchmarks.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 26 of its 35 references that are in the map. First posted on arXiv 10 Mar 2023.

Builds on

26 of 35 references.

References · 26

  1. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  2. 2017End-to-end Recovery of Human Shape and Posecited by 883
  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. 2020End-to-End Human Pose and Mesh Reconstruction with Transformerscited by 417
  6. 2020I2L-MeshNet: Image-to-Lixel Prediction Network for Accurate 3D Human Pose and Mesh Estimation from a Single RGB Imagecited by 274
  7. 2019Convolutional Mesh Regression for Single-Image Human Shape Reconstructioncited by 270
  8. 2021Mesh Graphormercited by 264
  9. 2017Integral Human Pose Regressioncited by 255
  10. 2021PyMAF: 3D Human Pose and Shape Regression with Pyramidal Mesh Alignment Feedback Loopcited by 250
  11. 2020Pose2Mesh: Graph Convolutional Network for 3D Human Pose and Mesh Recovery from a 2D Human Posecited by 248
  12. 2017Single-Shot Multi-Person 3D Pose Estimation From Monocular RGBcited by 195
14 more
  1. 2019Distribution-Aware Coordinate Representation for Human Pose Estimationcited by 165
  2. 2020Beyond Static Features for Temporally Consistent 3D Human Pose and Shape from a Videocited by 162
  3. 2021Probabilistic Modeling for Human Mesh Recoverycited by 152
  4. 2021MHFormer: Multi-Hypothesis Transformer for 3D Human Pose Estimationcited by 151
  5. 2022Recovering 3D Human Mesh from Monocular Images: A Surveycited by 103
  6. 2021Exploiting Temporal Contexts with Strided Transformer for 3D Human Pose Estimationcited by 94
  7. 2021Learning Skeletal Graph Neural Networks for Hard 3D Pose Estimationcited by 62
  8. 2022Capturing Humans in Motion: Temporal-Attentive 3D Human Pose and Shape Estimation from Monocular Videocited by 59
  9. 2022Occluded Human Mesh Recoverycited by 52
  10. 2021THUNDR: Transformer-based 3D HUmaN Reconstruction with Markerscited by 50
  11. 2021PC-HMR: Pose Calibration for 3D Human Mesh Recovery from 2D Images/Videoscited by 25
  12. 2021A Lightweight Graph Transformer Network for Human Mesh Reconstruction from 2D Human Posecited by 21
  13. 2022GraphMLP: A Graph MLP-Like Architecture for 3D Human Pose Estimationcited by 21
  14. 2022MUG: Multi-human Graph Network for 3D Mesh Reconstruction from 2D Posecited by 3

Built on by

Cited by year (2026 to 7 Oct)

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

4 papers.

  1. 2024DiffSurf: A Transformer-based Diffusion Model for Generating and Reconstructing 3D Surfaces in Posecited by 2
  2. 2024Dual-Branch Graph Transformer Network for 3D Human Mesh Reconstruction from Videocited by 1
  3. 2025MeshMamba: State Space Models for Articulated 3D Mesh Generation and Reconstructioncited by 1
  4. 2026Towards Geometry-Aware and Motion-Guided Video Human Mesh Recoverycited by 0