mlsanityData to 7 Oct 2026

Deep3DPose: Realtime Reconstruction of Arbitrarily Posed Human Bodies from Single RGB Images

arXiv 2106.11536 ↗First posted 22 Jun 2021cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

We introduce an approach that accurately reconstructs 3D human poses and detailed 3D full-body geometric models from single images in realtime. The key idea of our approach is a novel end-to-end multi-task deep learning framework that uses single images to predict five outputs simultaneously: foreground segmentation mask, 2D joints positions, semantic body partitions, 3D part orientations and uv coordinates (uv map). The multi-task network architecture not only generates more visual cues for reconstruction, but also makes each individual prediction more accurate. The CNN regressor is further combined with an optimization based algorithm for accurate kinematic pose reconstruction and full-body shape modeling. We show that the realtime reconstruction reaches accurate fitting that has not been seen before, especially for wild images. We demonstrate the results of our realtime 3D pose and human body reconstruction system on various challenging in-the-wild videos. We show the system advances the frontier of 3D human body and pose reconstruction from single images by quantitative evaluations and comparisons with state-of-the-art methods.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 37 of its 62 references that are in the map. First posted on arXiv 22 Jun 2021.

Builds on

37 of 62 references.

References · 37

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  3. 2015You Only Look Once: Unified, Real-Time Object Detectioncited by 4,829
  4. 2018MobileNetV2: Inverted Residuals and Linear Bottleneckscited by 4,773
  5. 2019Expressive Body Capture: 3D Hands, Face, and Body from a Single Imagecited by 1,600
  6. 2017Multi-Task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semanticscited by 1,345
  7. 2018OpenPose: Realtime Multi-Person 2D Pose Estimation using Part Affinity Fieldscited by 1,161
  8. 2016Realtime Multi-Person 2D Pose Estimation using Part Affinity Fieldscited by 1,061
  9. 2016Stacked Hourglass Networks for Human Pose Estimationcited by 913
  10. 2017End-to-end Recovery of Human Shape and Posecited by 883
  11. 2016Keep it SMPL: Automatic Estimation of 3D Human Pose and Shape from a Single Imagecited by 692
  12. 2019Learning to Reconstruct 3D Human Pose and Shape via Model-fitting in the Loopcited by 625
25 more
  1. 2019VIBE: Video Inference for Human Body Pose and Shape Estimationcited by 615
  2. 2018DensePose: Dense Human Pose Estimation In The Wildcited by 573
  3. 2016Monocular 3D Human Pose Estimation In The Wild Using Improved CNN Supervisioncited by 493
  4. 2017A simple yet effective baseline for 3d human pose estimationcited by 401
  5. 2016Convolutional Pose Machinescited by 325
  6. 2014Caffe: Convolutional Architecture for Fast Feature Embeddingcited by 287
  7. 2019Convolutional Mesh Regression for Single-Image Human Shape Reconstructioncited by 270
  8. 2017Integral Human Pose Regressioncited by 255
  9. 2018Total Capture: A 3D Deformation Model for Tracking Faces, Hands, and Bodiescited by 239
  10. 2016Coarse-to-Fine Volumetric Prediction for Single-Image 3D Human Posecited by 220
  11. 2017Unite the People: Closing the Loop Between 3D and 2D Human Representationscited by 205
  12. 2019Semantic Graph Convolutional Networks for 3D Human Pose Regressioncited by 204
  13. 2018Monocular Total Capture: Posing Face, Body, and Hands in the Wildcited by 162
  14. 2020DeepCap: Monocular Human Performance Capture Using Weak Supervisioncited by 162
  15. 2017Compositional Human Pose Regressioncited by 124
  16. 2017Towards 3D Human Pose Estimation in the Wild: a Weakly-supervised Approachcited by 114
  17. 2020Exemplar Fine-Tuning for 3D Human Model Fitting Towards In-the-Wild 3D Human Pose Estimationcited by 113
  18. 2018Ordinal Depth Supervision for 3D Human Pose Estimationcited by 107
  19. 2019DenseRaC: Joint 3D Pose and Shape Estimation by Dense Render-and-Comparecited by 100
  20. 2018LiveCap: Real-time Human Performance Capture from Monocular Videocited by 93
  21. 2019HEMlets Pose: Learning Part-Centric Heatmap Triplets for Accurate 3D Human Pose Estimationcited by 50
  22. 2019In the Wild Human Pose Estimation Using Explicit 2D Features and Intermediate 3D Representationscited by 48
  23. 2018OriNet: A Fully Convolutional Network for 3D Human Pose Estimationcited by 28
  24. 2017Deep Multitask Architecture for Integrated 2D and 3D Human Sensingcited by 21
  25. 2019DenseBody: Directly Regressing Dense 3D Human Pose and Shape From a Single Color Imagecited by 20

Built on by

Not cited yet.