mlsanityData to 14 Oct 2026

Sampling is Matter: Point-guided 3D Human Mesh Reconstruction

arXiv 2304.09502 ↗First posted 19 Apr 2023cs.CVcited by 24

Not on the map. Why?

Abstract (arXiv)

This paper presents a simple yet powerful method for 3D human mesh reconstruction from a single RGB image. Most recently, the non-local interactions of the whole mesh vertices have been effectively estimated in the transformer while the relationship between body parts also has begun to be handled via the graph model. Even though those approaches have shown the remarkable progress in 3D human mesh reconstruction, it is still difficult to directly infer the relationship between features, which are encoded from the 2D input image, and 3D coordinates of each vertex. To resolve this problem, we propose to design a simple feature sampling scheme. The key idea is to sample features in the embedded space by following the guide of points, which are estimated as projection results of 3D mesh vertices (i.e., ground truth). This helps the model to concentrate more on vertex-relevant features in the 2D space, thus leading to the reconstruction of the natural human pose. Furthermore, we apply progressive attention masking to precisely estimate local interactions between vertices even under severe occlusions. Experimental results on benchmark datasets show that the proposed method efficiently improves the performance of 3D human mesh reconstruction. The code and model are publicly available at: https://github.com/DCVL-3D/PointHMR_release.

Key facts. Cited by 24 papers in the map (data through 14 Oct 2026). Builds on 38 of its 45 references that are in the map. First posted on arXiv 19 Apr 2023.

Builds on

38 of 45 references.

References · 38

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  3. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  4. 2020End-to-End Object Detection with Transformerscited by 7,414
  5. 2016V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentationcited by 2,292
  6. 2019Expressive Body Capture: 3D Hands, Face, and Body from a Single Imagecited by 1,612
  7. 2019Deep High-Resolution Representation Learning for Visual Recognitioncited by 1,420
  8. 2017End-to-end Recovery of Human Shape and Posecited by 885
  9. 2016Keep it SMPL: Automatic Estimation of 3D Human Pose and Shape from a Single Imagecited by 695
  10. 2019Learning to Reconstruct 3D Human Pose and Shape via Model-fitting in the Loopcited by 627
  11. 2019VIBE: Video Inference for Human Body Pose and Shape Estimationcited by 620
  12. 2016Monocular 3D Human Pose Estimation In The Wild Using Improved CNN Supervisioncited by 494
26 more
  1. 2020End-to-End Human Pose and Mesh Reconstruction with Transformerscited by 418
  2. 2019Learning joint reconstruction of hands and manipulated objectscited by 378
  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. 2018CrowdHuman: A Benchmark for Detecting Human in a Crowdcited by 284
  6. 2020I2L-MeshNet: Image-to-Lixel Prediction Network for Accurate 3D Human Pose and Mesh Estimation from a Single RGB Imagecited by 274
  7. 2019FreiHAND: A Dataset for Markerless Capture of Hand Pose and Shape from Single RGB Imagescited by 271
  8. 2019Convolutional Mesh Regression for Single-Image Human Shape Reconstructioncited by 270
  9. 2018Generating 3D faces using Convolutional Mesh Autoencoderscited by 268
  10. 2021Mesh Graphormercited by 265
  11. 2021PyMAF: 3D Human Pose and Shape Regression with Pyramidal Mesh Alignment Feedback Loopcited by 250
  12. 2020Pose2Mesh: Graph Convolutional Network for 3D Human Pose and Mesh Recovery from a 2D Human Posecited by 248
  13. 2018Learning to Estimate 3D Human Pose and Shape from a Single Color Imagecited by 226
  14. 2020Monocular, One-stage, Regression of Multiple 3D Peoplecited by 218
  15. 2018CrowdPose: Efficient Crowded Scenes Pose Estimation and A New Benchmarkcited by 214
  16. 2017Unite the People: Closing the Loop Between 3D and 2D Human Representationscited by 205
  17. 2017Single-Shot Multi-Person 3D Pose Estimation From Monocular RGBcited by 195
  18. 20193D Hand Shape and Pose from Images in the Wildcited by 190
  19. 2020Monocular Expressive Body Regression through Body-Driven Attentioncited by 155
  20. 2021Putting People in their Place: Monocular Regression of 3D People in Depthcited by 142
  21. 2022Cross-Attention of Disentangled Modalities for 3D Human Mesh Recovery with Transformerscited by 81
  22. 2021Learning to Estimate Robust 3D Human Mesh from In-the-Wild Crowded Scenescited by 65
  23. 2021Encoder-decoder with Multi-level Attention for 3D Human Shape and Pose Estimationcited by 62
  24. 2022Occluded Human Mesh Recoverycited by 54
  25. 20203D Multi-bodies: Fitting Sets of Plausible 3D Human Models to Ambiguous Image Datacited by 50
  26. 2017MonoCap: Monocular Human Motion Capture using a CNN Coupled with a Geometric Priorcited by 36

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 1; 2024: 14; 2025: 6; 2026: 3.

24 papers.

Sort:

By area:

  1. 2024WiLoR: End-to-end 3D Hand Localization and Reconstruction in-the-wildcited by 124
  2. 2024Multi-HMR: Multi-Person Whole-Body Human Mesh Recovery in a Single Shotcited by 101
  3. 2024Hamba: Single-view 3D Hand Reconstruction with Graph-guided Bi-Scanning Mambacited by 45
  4. 2024A Simple Baseline for Efficient Hand Mesh Reconstructioncited by 27
  5. 2025GUAVA: Generalizable Upper Body 3D Gaussian Avatarcited by 22
  6. 2024MEGA: Masked Generative Autoencoder for Human Mesh Recoverycited by 14
  7. 2024HandOS: 3D Hand Reconstruction in One Stagecited by 9
  8. 2024MeshPose: Unifying DensePose and 3D Body Mesh reconstructioncited by 8
  9. 2025End-to-End HOI Reconstruction Transformer with Graph-based Encodingcited by 8
  10. 2024Human Mesh Recovery from Arbitrary Multi-view Imagescited by 6
  11. 2024Optimal-state Dynamics Estimation for Physics-based Human Motion Capture from Videoscited by 6
  12. 2024MaskHand: Generative Masked Modeling for Robust Hand Mesh Reconstruction in the Wildcited by 5
12 more
  1. 2025Towards Dynamic 3D Reconstruction of Hand-Instrument Interaction in Ophthalmic Surgerycited by 3
  2. 2026QuaMo: Quaternion Motions for Vision-based 3D Human Kinematics Capturecited by 3
  3. 2026EgoHandICL: Egocentric 3D Hand Reconstruction with In-Context Learningcited by 3
  4. 2024PostoMETRO: Pose Token Enhanced Mesh Transformer for Robust 3D Human Mesh Recoverycited by 2
  5. 2025MeshMamba: State Space Models for Articulated 3D Mesh Generation and Reconstructioncited by 2
  6. 2023Weakly-Supervised 3D Reconstruction of Clothed Humans via Normal Mapscited by 1
  7. 2024AdaptiveFusion: Adaptive Multi-Modal Multi-View Fusion for 3D Human Body Reconstructioncited by 1
  8. 2024RemoCap: Disentangled Representation Learning for Motion Capturecited by 0
  9. 2024ProGraph: Temporally-alignable Probability Guided Graph Topological Modeling for 3D Human Reconstructioncited by 0
  10. 2025M3DHMR: Monocular 3D Hand Mesh Recoverycited by 0
  11. 2025On the Use of Hierarchical Vision Foundation Models for Low-Cost Human Mesh Recovery and Pose Estimationcited by 0
  12. 2026B'ezier Degradation Modeling for LiDAR-based Human Motion Capturecited by 0