mlsanityData to 7 Oct 2026

Deep Virtual Markers for Articulated 3D Shapes

arXiv 2108.09000 ↗First posted 20 Aug 2021cs.CVcited by 7

Not on the map. Why?

Abstract (arXiv)

We propose deep virtual markers, a framework for estimating dense and accurate positional information for various types of 3D data. We design a concept and construct a framework that maps 3D points of 3D articulated models, like humans, into virtual marker labels. To realize the framework, we adopt a sparse convolutional neural network and classify 3D points of an articulated model into virtual marker labels. We propose to use soft labels for the classifier to learn rich and dense interclass relationships based on geodesic distance. To measure the localization accuracy of the virtual markers, we test FAUST challenge, and our result outperforms the state-of-the-art. We also observe outstanding performance on the generalizability test, unseen data evaluation, and different 3D data types (meshes and depth maps). We show additional applications using the estimated virtual markers, such as non-rigid registration, texture transfer, and realtime dense marker prediction from depth maps.

Key facts. Cited by 7 papers in the map (data through 7 Oct 2026). Builds on 35 of its 77 references that are in the map. First posted on arXiv 20 Aug 2021.

Builds on

35 of 77 references.

References · 35

  1. 2019KPConv: Flexible and Deformable Convolution for Point Cloudscited by 1,202
  2. 20194D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networkscited by 1,201
  3. 2016Stacked Hourglass Networks for Human Pose Estimationcited by 913
  4. 2016Keep it SMPL: Automatic Estimation of 3D Human Pose and Shape from a Single Imagecited by 692
  5. 2016Geometric deep learning on graphs and manifolds using mixture model CNNscited by 468
  6. 2017Learning from Synthetic Humanscited by 358
  7. 20163D Menagerie: Modeling the 3D shape and pose of animalscited by 310
  8. 2018Total Capture: A 3D Deformation Model for Tracking Faces, Hands, and Bodiescited by 239
  9. 2017Unite the People: Closing the Loop Between 3D and 2D Human Representationscited by 205
  10. 2020DeepCap: Monocular Human Performance Capture Using Weak Supervisioncited by 162
  11. 2017SplineCNN: Fast Geometric Deep Learning with Continuous B-Spline Kernelscited by 160
  12. 20183D-CODED : 3D Correspondences by Deep Deformationcited by 160
23 more
  1. 2017Deep Functional Maps: Structured Prediction for Dense Shape Correspondencecited by 134
  2. 2020Deep Geometric Functional Maps: Robust Feature Learning for Shape Correspondencecited by 125
  3. 2020LoopReg: Self-supervised Learning of Implicit Surface Correspondences, Pose and Shape for 3D Human Mesh Registrationcited by 108
  4. 2019Efficient Learning on Point Clouds with Basis Point Setscited by 101
  5. 2019Learning elementary structures for 3D shape generation and matchingcited by 98
  6. 2016Learning shape correspondence with anisotropic convolutional neural networkscited by 95
  7. 2018DoubleFusion: Real-time Capture of Human Performances with Inner Body Shapes from a Single Depth Sensorcited by 95
  8. 2018LiveCap: Real-time Human Performance Capture from Monocular Videocited by 93
  9. 2019SpiralNet++: A Fast and Highly Efficient Mesh Convolution Operatorcited by 89
  10. 2018Unsupervised Deep Learning for Structured Shape Matchingcited by 81
  11. 2018Continuous and Orientation-preserving Correspondences via Functional Mapscited by 77
  12. 2020Deep Shells: Unsupervised Shape Correspondence with Optimal Transportcited by 74
  13. 2019Smooth Shells: Multi-Scale Shape Registration with Functional Mapscited by 72
  14. 2019Learning from Synthetic Animalscited by 65
  15. 2020Correspondence Learning via Linearly-invariant Embeddingcited by 48
  16. 2017Joint Multi-Person Pose Estimation and Semantic Part Segmentationcited by 41
  17. 2018A Simple Approach to Intrinsic Correspondence Learning on Unstructured 3D Meshescited by 39
  18. 2019Cyclic Functional Mapping: Self-supervised correspondence between non-isometric deformable shapescited by 30
  19. 2015Dense Human Body Correspondences Using Convolutional Networkscited by 26
  20. 2018FARM: Functional Automatic Registration Method for 3D Human Bodiescited by 26
  21. 2014Semantic Part Segmentation using Compositional Model combining Shape and Appearancecited by 22
  22. 2019LBS Autoencoder: Self-supervised Fitting of Articulated Meshes to Point Cloudscited by 14
  23. 2020Learning Local Neighboring Structure for Robust 3D Shape Representationcited by 6

Built on by

Cited by year

Citing papers per year: 2021: 2; 2022: 0; 2023: 4; 2024: 1.

7 papers.

  1. 2021Multiway Non-rigid Point Cloud Registration via Learned Functional Map Synchronizationcited by 30
  2. 2023NICP: Neural ICP for 3D Human Registration at Scalecited by 21
  3. 2023Diffusion Shape Prior for Wrinkle-Accurate Cloth Registrationcited by 7
  4. 2023Stable and Consistent Prediction of 3D Characteristic Orientation via Invariant Residual Learningcited by 3
  5. 2021Putting 3D Spatially Sparse Networks on a Dietcited by 2
  6. 2023Skin Lesion Correspondence Localization in Total Body Photographycited by 2
  7. 2024Revisiting Lesion Tracking in 3D Total Body Photographycited by 0