mlsanityData to 14 Oct 2026

Implicit 3D Human Mesh Recovery using Consistency with Pose and Shape from Unseen-view

arXiv 2306.17651 ↗First posted 30 Jun 2023cs.CVcited by 8

Not on the map. Why?

Abstract (arXiv)

From an image of a person, we can easily infer the natural 3D pose and shape of the person even if ambiguity exists. This is because we have a mental model that allows us to imagine a person's appearance at different viewing directions from a given image and utilize the consistency between them for inference. However, existing human mesh recovery methods only consider the direction in which the image was taken due to their structural limitations. Hence, we propose "Implicit 3D Human Mesh Recovery (ImpHMR)" that can implicitly imagine a person in 3D space at the feature-level via Neural Feature Fields. In ImpHMR, feature fields are generated by CNN-based image encoder for a given image. Then, the 2D feature map is volume-rendered from the feature field for a given viewing direction, and the pose and shape parameters are regressed from the feature. To utilize consistency with pose and shape from unseen-view, if there are 3D labels, the model predicts results including the silhouette from an arbitrary direction and makes it equal to the rotated ground-truth. In the case of only 2D labels, we perform self-supervised learning through the constraint that the pose and shape parameters inferred from different directions should be the same. Extensive evaluations show the efficacy of the proposed method.

Key facts. Cited by 8 papers in the map (data through 14 Oct 2026). Builds on 55 of its 72 references that are in the map. First posted on arXiv 30 Jun 2023.

Builds on

55 of 72 references.

References · 55

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  3. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 7,005
  4. 2018CBAM: Convolutional Block Attention Modulecited by 2,477
  5. 2020Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domainscited by 2,200
  6. 2018Occupancy Networks: Learning 3D Reconstruction in Function Spacecited by 2,041
  7. 2019Expressive Body Capture: 3D Hands, Face, and Body from a Single Imagecited by 1,612
  8. 2019Deep High-Resolution Representation Learning for Human Pose Estimationcited by 1,339
  9. 2018Learning Implicit Fields for Generative Shape Modelingcited by 1,060
  10. 2017End-to-end Recovery of Human Shape and Posecited by 885
  11. 2020GIRAFFE: Representing Scenes as Compositional Generative Neural Feature Fieldscited by 785
  12. 2016Keep it SMPL: Automatic Estimation of 3D Human Pose and Shape from a Single Imagecited by 695
38 more
  1. 2020GRAF: Generative Radiance Fields for 3D-Aware Image Synthesiscited by 689
  2. 2019Learning to Reconstruct 3D Human Pose and Shape via Model-fitting in the Loopcited by 627
  3. 2019VIBE: Video Inference for Human Body Pose and Shape Estimationcited by 620
  4. 2016Monocular 3D Human Pose Estimation In The Wild Using Improved CNN Supervisioncited by 494
  5. 2017Neural 3D Mesh Renderercited by 437
  6. 2019Soft Rasterizer: A Differentiable Renderer for Image-based 3D Reasoningcited by 420
  7. 2020End-to-End Human Pose and Mesh Reconstruction with Transformerscited by 418
  8. 20183D human pose estimation in video with temporal convolutions and semi-supervised trainingcited by 403
  9. 2021PARE: Part Attention Regressor for 3D Human Body Estimationcited by 337
  10. 2018Learning 3D Human Dynamics from Videocited by 316
  11. 2020HybrIK: A Hybrid Analytical-Neural Inverse Kinematics Solution for 3D Human Pose and Shape Estimationcited by 307
  12. 2020I2L-MeshNet: Image-to-Lixel Prediction Network for Accurate 3D Human Pose and Mesh Estimation from a Single RGB Imagecited by 274
  13. 2019Convolutional Mesh Regression for Single-Image Human Shape Reconstructioncited by 270
  14. 2021Mesh Graphormercited by 265
  15. 2021PyMAF: 3D Human Pose and Shape Regression with Pyramidal Mesh Alignment Feedback Loopcited by 250
  16. 2020Pose2Mesh: Graph Convolutional Network for 3D Human Pose and Mesh Recovery from a 2D Human Posecited by 248
  17. 2018Total Capture: A 3D Deformation Model for Tracking Faces, Hands, and Bodiescited by 239
  18. 2018Learning to Estimate 3D Human Pose and Shape from a Single Color Imagecited by 226
  19. 2016Coarse-to-Fine Volumetric Prediction for Single-Image 3D Human Posecited by 221
  20. 2019Learning to Predict 3D Objects with an Interpolation-based Differentiable Renderercited by 221
  21. 2020Monocular, One-stage, Regression of Multiple 3D Peoplecited by 218
  22. 2017Unite the People: Closing the Loop Between 3D and 2D Human Representationscited by 205
  23. 2018Neural Body Fitting: Unifying Deep Learning and Model-Based Human Pose and Shape Estimationcited by 185
  24. 2020Beyond Static Features for Temporally Consistent 3D Human Pose and Shape from a Videocited by 163
  25. 2020Monocular Expressive Body Regression through Body-Driven Attentioncited by 155
  26. 2021Probabilistic Modeling for Human Mesh Recoverycited by 153
  27. 2018BodyNet: Volumetric Inference of 3D Human Body Shapescited by 141
  28. 2020Coherent Reconstruction of Multiple Humans from a Single Imagecited by 136
  29. 2019Exploiting temporal context for 3D human pose estimation in the wildcited by 110
  30. 2016Perspective Transformer Nets: Learning Single-View 3D Object Reconstruction without 3D Supervisioncited by 106
  31. 2019DenseRaC: Joint 3D Pose and Shape Estimation by Dense Render-and-Comparecited by 100
  32. 20203D Human Motion Estimation via Motion Compression and Refinementcited by 98
  33. 2017Self-supervised Learning of Motion Capturecited by 97
  34. 2020Weakly Supervised 3D Human Pose and Shape Reconstruction with Normalizing Flowscited by 94
  35. 2019Human Mesh Recovery from Monocular Images via a Skeleton-disentangled Representationcited by 87
  36. 2019Sim2real transfer learning for 3D human pose estimation: motion to the rescuecited by 76
  37. 2022Capturing Humans in Motion: Temporal-Attentive 3D Human Pose and Shape Estimation from Monocular Videocited by 60
  38. 2022Occluded Human Mesh Recoverycited by 54

50 most cited of 55 All 55 (JSON)

Built on by

Cited by year

Citing papers per year: 2023: 2; 2024: 5; 2025: 1.

8 papers.

  1. 2023Generative Approach for Probabilistic Human Mesh Recovery using Diffusion Modelscited by 14
  2. 2025ADHMR: Aligning Diffusion-based Human Mesh Recovery via Direct Preference Optimizationcited by 7
  3. 2024Distribution and Depth-Aware Transformers for 3D Human Mesh Recoverycited by 5
  4. 2024Diversifying Human Pose in Synthetic Data for Aerial-view Human Detectioncited by 5
  5. 2024KITRO: Refining Human Mesh by 2D Clues and Kinematic-tree Rotationcited by 5
  6. 2024Humans as Checkerboards: Calibrating Camera Motion Scale for World-Coordinate Human Mesh Recoverycited by 4
  7. 2024MoCap-to-Visual Domain Adaptation for Efficient Human Mesh Estimation from 2D Keypointscited by 3
  8. 2023PoseGen: Learning to Generate 3D Human Pose Dataset with NeRFcited by 2