mlsanityData to 14 Oct 2026

MeshPose: Unifying DensePose and 3D Body Mesh reconstruction

arXiv 2406.10180 ↗First posted 14 Jun 2024cs.CVcited by 8

Not on the map. Why?

Abstract (arXiv)

DensePose provides a pixel-accurate association of images with 3D mesh coordinates, but does not provide a 3D mesh, while Human Mesh Reconstruction (HMR) systems have high 2D reprojection error, as measured by DensePose localization metrics. In this work we introduce MeshPose to jointly tackle DensePose and HMR. For this we first introduce new losses that allow us to use weak DensePose supervision to accurately localize in 2D a subset of the mesh vertices ('VertexPose'). We then lift these vertices to 3D, yielding a low-poly body mesh ('MeshPose'). Our system is trained in an end-to-end manner and is the first HMR method to attain competitive DensePose accuracy, while also being lightweight and amenable to efficient inference, making it suitable for real-time AR applications.

Key facts. Cited by 8 papers in the map (data through 14 Oct 2026). Builds on 49 of its 62 references that are in the map. First posted on arXiv 14 Jun 2024.

Builds on

49 of 62 references.

References · 49

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  3. 2018MobileNetV2: Inverted Residuals and Linear Bottleneckscited by 4,795
  4. 2019Expressive Body Capture: 3D Hands, Face, and Body from a Single Imagecited by 1,612
  5. 2019Deep High-Resolution Representation Learning for Visual Recognitioncited by 1,420
  6. 2017End-to-end Recovery of Human Shape and Posecited by 885
  7. 2019Learning to Reconstruct 3D Human Pose and Shape via Model-fitting in the Loopcited by 627
  8. 2019VIBE: Video Inference for Human Body Pose and Shape Estimationcited by 620
  9. 2018DensePose: Dense Human Pose Estimation In The Wildcited by 575
  10. 2018Simple Baselines for Human Pose Estimation and Trackingcited by 502
  11. 2016Monocular 3D Human Pose Estimation In The Wild Using Improved CNN Supervisioncited by 494
  12. 2019Soft Rasterizer: A Differentiable Renderer for Image-based 3D Reasoningcited by 420
37 more
  1. 2020End-to-End Human Pose and Mesh Reconstruction with Transformerscited by 418
  2. 2023Humans in 4D: Reconstructing and Tracking Humans with Transformerscited by 350
  3. 2021PARE: Part Attention Regressor for 3D Human Body Estimationcited by 337
  4. 2020HybrIK: A Hybrid Analytical-Neural Inverse Kinematics Solution for 3D Human Pose and Shape Estimationcited by 307
  5. 2019Resolving 3D Human Pose Ambiguities with 3D Scene Constraintscited by 295
  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 265
  9. 2021PyMAF: 3D Human Pose and Shape Regression with Pyramidal Mesh Alignment Feedback Loopcited by 250
  10. 2020Pose2Mesh: Graph Convolutional Network for 3D Human Pose and Mesh Recovery from a 2D Human Posecited by 248
  11. 2022CLIFF: Carrying Location Information in Full Frames into Human Pose and Shape Estimationcited by 238
  12. 2018Learning to Estimate 3D Human Pose and Shape from a Single Color Imagecited by 226
  13. 2020Monocular, One-stage, Regression of Multiple 3D Peoplecited by 218
  14. 2018Boundary loss for highly unbalanced segmentationcited by 190
  15. 2020Beyond Static Features for Temporally Consistent 3D Human Pose and Shape from a Videocited by 163
  16. 2021Probabilistic Modeling for Human Mesh Recoverycited by 153
  17. 2021Putting People in their Place: Monocular Regression of 3D People in Depthcited by 142
  18. 2020Coherent Reconstruction of Multiple Humans from a Single Imagecited by 136
  19. 2021SPEC: Seeing People in the Wild with an Estimated Cameracited by 135
  20. 2019Camera Distance-aware Top-down Approach for 3D Multi-person Pose Estimation from a Single RGB Imagecited by 132
  21. 2020Weakly Supervised 3D Human Pose and Shape Reconstruction with Normalizing Flowscited by 94
  22. 2021On Self-Contact and Human Posecited by 89
  23. 2020Human Body Model Fitting by Learned Gradient Descentcited by 81
  24. 2022Cross-Attention of Disentangled Modalities for 3D Human Mesh Recovery with Transformerscited by 81
  25. 2020NeuralAnnot: Neural Annotator for 3D Human Mesh Training Setscited by 62
  26. 2022Occluded Human Mesh Recoverycited by 54
  27. 2021Style and Pose Control for Image Synthesis of Humans from a Single Monocular Viewcited by 53
  28. 2019Learning 3D Human Shape and Pose from Dense Body Partscited by 48
  29. 2023ReFit: Recurrent Fitting Network for 3D Human Recoverycited by 47
  30. 2023NIKI: Neural Inverse Kinematics with Invertible Neural Networks for 3D Human Pose and Shape Estimationcited by 45
  31. 20233D Human Mesh Estimation from Virtual Markerscited by 44
  32. 2023Zolly: Zoom Focal Length Correctly for Perspective-Distorted Human Mesh Reconstructioncited by 41
  33. 2022Learned Vertex Descent: A New Direction for 3D Human Model Fittingcited by 37
  34. 2021KAMA: 3D Keypoint Aware Body Mesh Articulationcited by 27
  35. 2023Sampling is Matter: Point-guided 3D Human Mesh Reconstructioncited by 24
  36. 2022PLIKS: A Pseudo-Linear Inverse Kinematic Solver for 3D Human Body Estimationcited by 18
  37. 2022Learning Visibility for Robust Dense Human Body Estimationcited by 15

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 1; 2025: 3; 2026: 4.

8 papers.

  1. 2026QuaMo: Quaternion Motions for Vision-based 3D Human Kinematics Capturecited by 3
  2. 2024HeatFormer: A Neural Optimizer for Multiview Human Mesh Recoverycited by 2
  3. 2025ClothHMR: 3D Mesh Recovery of Humans in Diverse Clothing from Single Imagecited by 1
  4. 2026DiffProxy: Multi-View Human Mesh Recovery via Diffusion-Generated Dense Proxiescited by 1
  5. 2025Human Pose-Constrained UV Map Estimationcited by 0
  6. 2025On the Use of Hierarchical Vision Foundation Models for Low-Cost Human Mesh Recovery and Pose Estimationcited by 0
  7. 2026MoPO: Incorporating Motion Prior for Occluded Human Mesh Recoverycited by 0
  8. 2026MuNet: A Mutualistic Network for Joint 3D Human Mesh Recovery and 3D Clothed Human Reconstruction from Single Imagescited by 0