mlsanityData to 7 Oct 2026

DensePose 3D: Lifting Canonical Surface Maps of Articulated Objects to the Third Dimension

arXiv 2109.00033 ↗First posted 31 Aug 2021cs.CVcited by 5

Not on the map. Why?

Abstract (arXiv)

We tackle the problem of monocular 3D reconstruction of articulated objects like humans and animals. We contribute DensePose 3D, a method that can learn such reconstructions in a weakly supervised fashion from 2D image annotations only. This is in stark contrast with previous deformable reconstruction methods that use parametric models such as SMPL pre-trained on a large dataset of 3D object scans. Because it does not require 3D scans, DensePose 3D can be used for learning a wide range of articulated categories such as different animal species. The method learns, in an end-to-end fashion, a soft partition of a given category-specific 3D template mesh into rigid parts together with a monocular reconstruction network that predicts the part motions such that they reproject correctly onto 2D DensePose-like surface annotations of the object. The decomposition of the object into parts is regularized by expressing part assignments as a combination of the smooth eigenfunctions of the Laplace-Beltrami operator. We show significant improvements compared to state-of-the-art non-rigid structure-from-motion baselines on both synthetic and real data on categories of humans and animals.

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Builds on 40 of its 66 references that are in the map. First posted on arXiv 31 Aug 2021.

Builds on

40 of 66 references.

References · 40

  1. 2019Expressive Body Capture: 3D Hands, Face, and Body from a Single Imagecited by 1,600
  2. 2019LVIS: A Dataset for Large Vocabulary Instance Segmentationcited by 1,215
  3. 2017End-to-end Recovery of Human Shape and Posecited by 883
  4. 2016Keep it SMPL: Automatic Estimation of 3D Human Pose and Shape from a Single Imagecited by 692
  5. 2019Learning to Reconstruct 3D Human Pose and Shape via Model-fitting in the Loopcited by 625
  6. 2018DensePose: Dense Human Pose Estimation In The Wildcited by 573
  7. 2017A simple yet effective baseline for 3d human pose estimationcited by 401
  8. 2018Learning Category-Specific Mesh Reconstruction from Image Collectionscited by 317
  9. 2019Convolutional Mesh Regression for Single-Image Human Shape Reconstructioncited by 270
  10. 2017Integral Human Pose Regressioncited by 255
  11. 2018Total Capture: A 3D Deformation Model for Tracking Faces, Hands, and Bodiescited by 239
  12. 2019Learning to Predict 3D Objects with an Interpolation-based Differentiable Renderercited by 221
28 more
  1. 2017Unite the People: Closing the Loop Between 3D and 2D Human Representationscited by 205
  2. 2018Monocular Total Capture: Posing Face, Body, and Hands in the Wildcited by 162
  3. 2017VNect: Real-time 3D Human Pose Estimation with a Single RGB Cameracited by 129
  4. 2018Ordinal Depth Supervision for 3D Human Pose Estimationcited by 107
  5. 2019Self-Supervised Learning of 3D Human Pose using Multi-view Geometrycited by 98
  6. 2019Unsupervised 3D Pose Estimation with Geometric Self-Supervisioncited by 95
  7. 2017Towards Accurate Markerless Human Shape and Pose Estimation over Timecited by 92
  8. 2018LCR-Net++: Multi-person 2D and 3D Pose Detection in Natural Imagescited by 88
  9. 2018Creatures great and SMAL: Recovering the shape and motion of animals from videocited by 84
  10. 2020Who Left the Dogs Out? 3D Animal Reconstruction with Expectation Maximization in the Loopcited by 81
  11. 2020Articulation-aware Canonical Surface Mappingcited by 80
  12. 2020Continuous Surface Embeddingscited by 79
  13. 2018Learning Monocular 3D Human Pose Estimation from Multi-view Imagescited by 70
  14. 2019Canonical Surface Mapping via Geometric Cycle Consistencycited by 62
  15. 2019C3DPO: Canonical 3D Pose Networks for Non-Rigid Structure From Motioncited by 60
  16. 2020Neural Descent for Visual 3D Human Pose and Shapecited by 60
  17. 2015Sparseness Meets Deepness: 3D Human Pose Estimation from Monocular Videocited by 54
  18. 20203D Multi-bodies: Fitting Sets of Plausible 3D Human Models to Ambiguous Image Datacited by 50
  19. 2017Harvesting Multiple Views for Marker-less 3D Human Pose Annotationscited by 48
  20. 2018Can 3D Pose be Learned from 2D Projections Alone?cited by 44
  21. 2019Deep Non-Rigid Structure from Motioncited by 38
  22. 2020Transferring Dense Pose to Proximal Animal Classescited by 23
  23. 2018Scalable Dense Non-rigid Structure-from-Motion: A Grassmannian Perspectivecited by 19
  24. 2018Unsupervised Adversarial Learning of 3D Human Pose from 2D Joint Locationscited by 18
  25. 2015Sparse Representation for 3D Shape Estimation: A Convex Relaxation Approachcited by 16
  26. 2019Slim DensePose: Thrifty Learning from Sparse Annotations and Motion Cuescited by 13
  27. 2020Deep NRSfM++: Towards Unsupervised 2D-3D Lifting in the Wildcited by 10
  28. 2017Spatial-Temporal Union of Subspaces for Multi-body Non-rigid Structure-from-Motioncited by 2

Built on by

Cited by year

Citing papers per year: 2022: 2; 2023: 1; 2024: 1; 2025: 1.

5 papers.

  1. 2024Neural Localizer Fields for Continuous 3D Human Pose and Shape Estimationcited by 57
  2. 2023Improving Semantic Correspondence with Viewpoint-Guided Spherical Mapscited by 33
  3. 2022State of the Art in Dense Monocular Non-Rigid 3D Reconstructioncited by 30
  4. 2022DensePose From WiFicited by 12
  5. 20253D Human Mesh Estimation from Single View RGBDcited by 0