mlsanityData to 7 Oct 2026

Three Recipes for Better 3D Pseudo-GTs of 3D Human Mesh Estimation in the Wild

arXiv 2304.04875 ↗First posted 10 Apr 2023cs.CVcited by 9

Not on the map. Why?

Abstract (arXiv)

Recovering 3D human mesh in the wild is greatly challenging as in-the-wild (ITW) datasets provide only 2D pose ground truths (GTs). Recently, 3D pseudo-GTs have been widely used to train 3D human mesh estimation networks as the 3D pseudo-GTs enable 3D mesh supervision when training the networks on ITW datasets. However, despite the great potential of the 3D pseudo-GTs, there has been no extensive analysis that investigates which factors are important to make more beneficial 3D pseudo-GTs. In this paper, we provide three recipes to obtain highly beneficial 3D pseudo-GTs of ITW datasets. The main challenge is that only 2D-based weak supervision is allowed when obtaining the 3D pseudo-GTs. Each of our three recipes addresses the challenge in each aspect: depth ambiguity, sub-optimality of weak supervision, and implausible articulation. Experimental results show that simply re-training state-of-the-art networks with our new 3D pseudo-GTs elevates their performance to the next level without bells and whistles. The 3D pseudo-GT is publicly available in https://github.com/mks0601/NeuralAnnot_RELEASE.

Key facts. Cited by 9 papers in the map (data through 7 Oct 2026). Builds on 38 of its 50 references that are in the map. First posted on arXiv 10 Apr 2023.

Builds on

38 of 50 references.

References · 38

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  4. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,441
  5. 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,482
  6. 2020Bootstrap your own latent: A new approach to self-supervised Learningcited by 4,712
  7. 2019Expressive Body Capture: 3D Hands, Face, and Body from a Single Imagecited by 1,600
  8. 2019AMASS: Archive of Motion Capture as Surface Shapescited by 1,208
  9. 2017End-to-end Recovery of Human Shape and Posecited by 883
  10. 2016Keep it SMPL: Automatic Estimation of 3D Human Pose and Shape from a Single Imagecited by 692
  11. 2019Learning to Reconstruct 3D Human Pose and Shape via Model-fitting in the Loopcited by 625
  12. 2019VIBE: Video Inference for Human Body Pose and Shape Estimationcited by 615
26 more
  1. 2018Simple Baselines for Human Pose Estimation and Trackingcited by 502
  2. 2016Monocular 3D Human Pose Estimation In The Wild Using Improved CNN Supervisioncited by 493
  3. 2020End-to-End Human Pose and Mesh Reconstruction with Transformerscited by 417
  4. 2021PARE: Part Attention Regressor for 3D Human Body Estimationcited by 334
  5. 2018Learning 3D Human Dynamics from Videocited by 315
  6. 2020HybrIK: A Hybrid Analytical-Neural Inverse Kinematics Solution for 3D Human Pose and Shape Estimationcited by 304
  7. 2020I2L-MeshNet: Image-to-Lixel Prediction Network for Accurate 3D Human Pose and Mesh Estimation from a Single RGB Imagecited by 274
  8. 2021Mesh Graphormercited by 264
  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. 2020InterHand2.6M: A Dataset and Baseline for 3D Interacting Hand Pose Estimation from a Single RGB Imagecited by 244
  12. 2022CLIFF: Carrying Location Information in Full Frames into Human Pose and Shape Estimationcited by 237
  13. 2020Monocular, One-stage, Regression of Multiple 3D Peoplecited by 216
  14. 2017Single-Shot Multi-Person 3D Pose Estimation From Monocular RGBcited by 195
  15. 2015Weakly Supervised Deep Detection Networkscited by 183
  16. 2020Beyond Static Features for Temporally Consistent 3D Human Pose and Shape from a Videocited by 162
  17. 2021Efficient Visual Pretraining with Contrastive Detectioncited by 150
  18. 2020Coherent Reconstruction of Multiple Humans from a Single Imagecited by 136
  19. 2020Evaluating Weakly Supervised Object Localization Methods Rightcited by 104
  20. 2018PCL: Proposal Cluster Learning for Weakly Supervised Object Detectioncited by 97
  21. 2020Accurate 3D Hand Pose Estimation for Whole-Body 3D Human Mesh Estimationcited by 81
  22. 2019C-MIL: Continuation Multiple Instance Learning for Weakly Supervised Object Detectioncited by 71
  23. 2021Learning to Estimate Robust 3D Human Mesh from In-the-Wild Crowded Scenescited by 64
  24. 2020NeuralAnnot: Neural Annotator for 3D Human Mesh Training Setscited by 62
  25. 20223D Clothed Human Reconstruction in the Wildcited by 41
  26. 2020Evaluation for Weakly Supervised Object Localization: Protocol, Metrics, and Datasetscited by 19

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 3; 2024: 2; 2025: 3; 2026: 1.

9 papers.

  1. 2023Motion-X: A Large-scale 3D Expressive Whole-body Human Motion Datasetcited by 220
  2. 2023WHAM: Reconstructing World-grounded Humans with Accurate 3D Motioncited by 200
  3. 2024Multi-HMR: Multi-Person Whole-Body Human Mesh Recovery in a Single Shotcited by 98
  4. 2025HumanMM: Global Human Motion Recovery from Multi-shot Videoscited by 4
  5. 2024PostoMETRO: Pose Token Enhanced Mesh Transformer for Robust 3D Human Mesh Recoverycited by 2
  6. 2025PoseSyn: Synthesizing Diverse 3D Pose Data from In-the-Wild 2D Datacited by 1
  7. 2025PoseBH: Prototypical Multi-Dataset Training Beyond Human Pose Estimationcited by 1
  8. 2023QPoser: Quantized Explicit Pose Prior Modeling for Controllable Pose Generationcited by 0
  9. 2026PoseDreamer: Scalable and Photorealistic Human Data Generation Pipeline with Diffusion Modelscited by 0