mlsanityData to 7 Oct 2026

D-PoSE: Depth as an Intermediate Representation for 3D Human Pose and Shape Estimation

arXiv 2410.04889 ↗First posted 7 Oct 2024cs.CVcited by 1

Not on the map. Why?

Abstract (arXiv)

We present D-PoSE (Depth as an Intermediate Representation for 3D Human Pose and Shape Estimation), a one-stage method that estimates human pose and SMPL-X shape parameters from a single RGB image. Recent works use larger models with transformer backbones and decoders to improve the accuracy in human pose and shape (HPS) benchmarks. D-PoSE proposes a vision based approach that uses the estimated human depth-maps as an intermediate representation for HPS and leverages training with synthetic data and the ground-truth depth-maps provided with them for depth supervision during training. Although trained on synthetic datasets, D-PoSE achieves state-of-the-art performance on the real-world benchmark datasets, EMDB and 3DPW. Despite its simple lightweight design and the CNN backbone, it outperforms ViT-based models that have a number of parameters that is larger by almost an order of magnitude. D-PoSE code is available at: https://github.com/nvasilik/D-PoSE

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 53 of its 60 references that are in the map. First posted on arXiv 7 Oct 2024.

Builds on

53 of 60 references.

References · 53

  1. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  2. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  3. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  4. 2019Expressive Body Capture: 3D Hands, Face, and Body from a Single Imagecited by 1,600
  5. 2019Deep High-Resolution Representation Learning for Visual Recognitioncited by 1,417
  6. 2019Deep High-Resolution Representation Learning for Human Pose Estimationcited by 1,339
  7. 2016Realtime Multi-Person 2D Pose Estimation using Part Affinity Fieldscited by 1,061
  8. 2017End-to-end Recovery of Human Shape and Posecited by 883
  9. 2016Keep it SMPL: Automatic Estimation of 3D Human Pose and Shape from a Single Imagecited by 692
  10. 2019Learning to Reconstruct 3D Human Pose and Shape via Model-fitting in the Loopcited by 625
  11. 2019VIBE: Video Inference for Human Body Pose and Shape Estimationcited by 615
  12. 2018DensePose: Dense Human Pose Estimation In The Wildcited by 573
38 more
  1. 2018Albumentations: fast and flexible image augmentationscited by 558
  2. 2020PIFuHD: Multi-Level Pixel-Aligned Implicit Function for High-Resolution 3D Human Digitizationcited by 521
  3. 2022ViTPose: Simple Vision Transformer Baselines for Human Pose Estimationcited by 450
  4. 2017Neural 3D Mesh Renderercited by 437
  5. 2020End-to-End Human Pose and Mesh Reconstruction with Transformerscited by 417
  6. 2017Learning from Synthetic Humanscited by 358
  7. 2023Humans in 4D: Reconstructing and Tracking Humans with Transformerscited by 344
  8. 2021PARE: Part Attention Regressor for 3D Human Body Estimationcited by 334
  9. 2020HybrIK: A Hybrid Analytical-Neural Inverse Kinematics Solution for 3D Human Pose and Shape Estimationcited by 304
  10. 20213D Human Pose Estimation with Spatial and Temporal Transformerscited by 271
  11. 2019Convolutional Mesh Regression for Single-Image Human Shape Reconstructioncited by 270
  12. 2021Mesh Graphormercited by 264
  13. 2019HigherHRNet: Scale-Aware Representation Learning for Bottom-Up Human Pose Estimationcited by 247
  14. 2022CLIFF: Carrying Location Information in Full Frames into Human Pose and Shape Estimationcited by 237
  15. 2023BEDLAM: A Synthetic Dataset of Bodies Exhibiting Detailed Lifelike Animated Motioncited by 229
  16. 2020Monocular, One-stage, Regression of Multiple 3D Peoplecited by 216
  17. 2017Unite the People: Closing the Loop Between 3D and 2D Human Representationscited by 205
  18. 2021AGORA: Avatars in Geography Optimized for Regression Analysiscited by 203
  19. 2022ECON: Explicit Clothed humans Optimized via Normal integrationcited by 199
  20. 2018Neural Body Fitting: Unifying Deep Learning and Model-Based Human Pose and Shape Estimationcited by 185
  21. 2022Capturing and Inferring Dense Full-Body Human-Scene Contactcited by 176
  22. 2018Monocular Total Capture: Posing Face, Body, and Hands in the Wildcited by 162
  23. 2021Probabilistic Modeling for Human Mesh Recoverycited by 152
  24. 2021Putting People in their Place: Monocular Regression of 3D People in Depthcited by 141
  25. 2019PifPaf: Composite Fields for Human Pose Estimationcited by 120
  26. 2023EMDB: The Electromagnetic Database of Global 3D Human Pose and Shape in the Wildcited by 95
  27. 2020SRNet: Improving Generalization in 3D Human Pose Estimation with a Split-and-Recombine Approachcited by 94
  28. 2024TokenHMR: Advancing Human Mesh Recovery with a Tokenized Pose Representationcited by 93
  29. 2019Detailed Human Shape Estimation from a Single Image by Hierarchical Mesh Deformationcited by 71
  30. 2020Hierarchical Kinematic Human Mesh Recoverycited by 71
  31. 2021Self-Supervised Monocular Depth Estimation with Internal Feature Fusioncited by 67
  32. 2021Learning to Estimate Robust 3D Human Mesh from In-the-Wild Crowded Scenescited by 64
  33. 2022Capturing Humans in Motion: Temporal-Attentive 3D Human Pose and Shape Estimation from Monocular Videocited by 59
  34. 2022COAP: Compositional Articulated Occupancy of Peoplecited by 59
  35. 2023ReFit: Recurrent Fitting Network for 3D Human Recoverycited by 47
  36. 2021Learning to Regress Bodies from Images using Differentiable Semantic Renderingcited by 39
  37. 2020MeTRAbs: Metric-Scale Truncation-Robust Heatmaps for Absolute 3D Human Pose Estimationcited by 35
  38. 2023POCO: 3D Pose and Shape Estimation with Confidencecited by 20

50 most cited of 53 All 53 (JSON)

Built on by

Cited by year

Citing papers per year: 2025: 1.

1 paper.

  1. 2025Ice Hockey Puck Localization Using Contextual Cuescited by 0