mlsanityData to 14 Oct 2026

Domain Adaptive 3D Pose Augmentation for In-the-wild Human Mesh Recovery

arXiv 2206.10457 ↗First posted 21 Jun 2022cs.CVcited by 12

Not on the map. Why?

Abstract (arXiv)

The ability to perceive 3D human bodies from a single image has a multitude of applications ranging from entertainment and robotics to neuroscience and healthcare. A fundamental challenge in human mesh recovery is in collecting the ground truth 3D mesh targets required for training, which requires burdensome motion capturing systems and is often limited to indoor laboratories. As a result, while progress is made on benchmark datasets collected in these restrictive settings, models fail to generalize to real-world "in-the-wild" scenarios due to distribution shifts. We propose Domain Adaptive 3D Pose Augmentation (DAPA), a data augmentation method that enhances the model's generalization ability in in-the-wild scenarios. DAPA combines the strength of methods based on synthetic datasets by getting direct supervision from the synthesized meshes, and domain adaptation methods by using ground truth 2D keypoints from the target dataset. We show quantitatively that finetuning with DAPA effectively improves results on benchmarks 3DPW and AGORA. We further demonstrate the utility of DAPA on a challenging dataset curated from videos of real-world parent-child interaction.

Key facts. Cited by 12 papers in the map (data through 14 Oct 2026). Builds on 35 of its 45 references that are in the map. First posted on arXiv 21 Jun 2022.

Builds on

35 of 45 references.

References · 35

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  3. 2019Expressive Body Capture: 3D Hands, Face, and Body from a Single Imagecited by 1,612
  4. 2019AMASS: Archive of Motion Capture as Surface Shapescited by 1,236
  5. 2018OpenPose: Realtime Multi-Person 2D Pose Estimation using Part Affinity Fieldscited by 1,162
  6. 2017End-to-end Recovery of Human Shape and Posecited by 885
  7. 2016Keep it SMPL: Automatic Estimation of 3D Human Pose and Shape from a Single Imagecited by 695
  8. 2019Learning to Reconstruct 3D Human Pose and Shape via Model-fitting in the Loopcited by 627
  9. 2016Monocular 3D Human Pose Estimation In The Wild Using Improved CNN Supervisioncited by 494
  10. 2017Neural 3D Mesh Renderercited by 437
  11. 2017Learning from Synthetic Humanscited by 359
  12. 2021PARE: Part Attention Regressor for 3D Human Body Estimationcited by 337
23 more
  1. 2018Learning Category-Specific Mesh Reconstruction from Image Collectionscited by 317
  2. 2021Mesh Graphormercited by 265
  3. 2017Unite the People: Closing the Loop Between 3D and 2D Human Representationscited by 205
  4. 2021AGORA: Avatars in Geography Optimized for Regression Analysiscited by 205
  5. 2019Distribution-Aware Coordinate Representation for Human Pose Estimationcited by 165
  6. 2020Populating 3D Scenes by Learning Human-Scene Interactioncited by 164
  7. 2021SPEC: Seeing People in the Wild with an Estimated Cameracited by 135
  8. 2019Generating 3D People in Scenes without Peoplecited by 127
  9. 2020Exemplar Fine-Tuning for 3D Human Model Fitting Towards In-the-Wild 3D Human Pose Estimationcited by 113
  10. 2021PoseAug: A Differentiable Pose Augmentation Framework for 3D Human Pose Estimationcited by 89
  11. 2021S3: Neural Shape, Skeleton, and Skinning Fields for 3D Human Modelingcited by 59
  12. 20203D Human Pose Estimation using Spatio-Temporal Networks with Explicit Occlusion Trainingcited by 54
  13. 2020Holistic 3D Human and Scene Mesh Estimation from Single View Imagescited by 54
  14. 2016Synthesizing Training Images for Boosting Human 3D Pose Estimationcited by 52
  15. 20203D Multi-bodies: Fitting Sets of Plausible 3D Human Models to Ambiguous Image Datacited by 50
  16. 2019In the Wild Human Pose Estimation Using Explicit 2D Features and Intermediate 3D Representationscited by 48
  17. 2021Bilevel Online Adaptation for Out-of-Domain Human Mesh Reconstructioncited by 39
  18. 2020Bodies at Rest: 3D Human Pose and Shape Estimation from a Pressure Image using Synthetic Datacited by 34
  19. 2020Vid2Player: Controllable Video Sprites that Behave and Appear like Professional Tennis Playerscited by 30
  20. 2020Full-Body Awareness from Partial Observationscited by 29
  21. 2020Reconstructing NBA Playerscited by 24
  22. 2018How Robust is 3D Human Pose Estimation to Occlusion?cited by 23
  23. 2021Tracking People with 3D Representationscited by 22

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 1; 2023: 4; 2024: 3; 2025: 3; 2026: 1.

12 papers.

  1. 2024Template-Free Single-View 3D Human Digitalization with Diffusion-Guided LRMcited by 23
  2. 2023ZeroAvatar: Zero-shot 3D Avatar Generation from a Single Imagecited by 18
  3. 2023Cyclic Test-Time Adaptation on Monocular Video for 3D Human Mesh Reconstructioncited by 18
  4. 2023KBody: Towards general, robust, and aligned monocular whole-body estimationcited by 6
  5. 2023Diffusion-HPC: Synthetic Data Generation for Human Mesh Recovery in Challenging Domainscited by 5
  6. 2022NeMo: 3D Neural Motion Fields from Multiple Video Instances of the Same Actioncited by 2
  7. 2024ESCAPE: Energy-based Selective Adaptive Correction for Out-of-distribution 3D Human Pose Estimationcited by 1
  8. 2024Ask, Pose, Unite: Scaling Data Acquisition for Close Interactions with Vision Language Modelscited by 1
  9. 2025Semantics-aware Test-time Adaptation for 3D Human Pose Estimationcited by 1
  10. 2025Online Test-time Adaptation for 3D Human Pose Estimation: A Practical Perspective with Estimated 2D Posescited by 1
  11. 2025Robust Long-term Test-Time Adaptation for 3D Human Pose Estimation through Motion Discretizationcited by 0
  12. 2026UnrealPose: Leveraging Game Engine Kinematics for Large-Scale Synthetic Human Pose Datacited by 0