mlsanityData to 14 Oct 2026

Occlusion Resilient 3D Human Pose Estimation

arXiv 2402.11036 ↗First posted 16 Feb 2024cs.CV cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Occlusions remain one of the key challenges in 3D body pose estimation from single-camera video sequences. Temporal consistency has been extensively used to mitigate their impact but the existing algorithms in the literature do not explicitly model them. Here, we apply this by representing the deforming body as a spatio-temporal graph. We then introduce a refinement network that performs graph convolutions over this graph to output 3D poses. To ensure robustness to occlusions, we train this network with a set of binary masks that we use to disable some of the edges as in drop-out techniques. In effect, we simulate the fact that some joints can be hidden for periods of time and train the network to be immune to that. We demonstrate the effectiveness of this approach compared to state-of-the-art techniques that infer poses from single-camera sequences.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 35 of its 53 references that are in the map. First posted on arXiv 16 Feb 2024.

Builds on

35 of 53 references.

References · 35

  1. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
  2. 2015Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learningcited by 4,448
  3. 2016Convolutional Neural Networks on Graphs with Fast Localized Spectral Filteringcited by 2,089
  4. 2016Monocular 3D Human Pose Estimation In The Wild Using Improved CNN Supervisioncited by 494
  5. 20183D human pose estimation in video with temporal convolutions and semi-supervised trainingcited by 403
  6. 2017A simple yet effective baseline for 3d human pose estimationcited by 401
  7. 2017Cascaded Pyramid Network for Multi-Person Pose Estimationcited by 341
  8. 2018Learning 3D Human Dynamics from Videocited by 316
  9. 2017Integral Human Pose Regressioncited by 256
  10. 2016Coarse-to-Fine Volumetric Prediction for Single-Image 3D Human Posecited by 221
  11. 2017CayleyNets: Graph Convolutional Neural Networks with Complex Rational Spectral Filterscited by 203
  12. 2019Learnable Triangulation of Human Posecited by 161
23 more
  1. 2017Compositional Human Pose Regressioncited by 124
  2. 2017Towards 3D Human Pose Estimation in the Wild: a Weakly-supervised Approachcited by 115
  3. 2018Hand Pose Estimation via Latent 2.5D Heatmap Regressioncited by 111
  4. 2019Self-Supervised Learning of 3D Human Pose using Multi-view Geometrycited by 98
  5. 2019Unsupervised 3D Pose Estimation with Geometric Self-Supervisioncited by 95
  6. 2021Graph Stacked Hourglass Networks for 3D Human Pose Estimationcited by 95
  7. 2020SRNet: Improving Generalization in 3D Human Pose Estimation with a Split-and-Recombine Approachcited by 94
  8. 2017Exploiting temporal information for 3D pose estimationcited by 89
  9. 20183D Human Pose Estimation in the Wild by Adversarial Learningcited by 86
  10. 2018Unsupervised Geometry-Aware Representation for 3D Human Pose Estimationcited by 73
  11. 2018Learning Monocular 3D Human Pose Estimation from Multi-view Imagescited by 70
  12. 2020Weakly-Supervised 3D Human Pose Learning via Multi-view Images in the Wildcited by 66
  13. 2019TexturePose: Supervising Human Mesh Estimation with Texture Consistencycited by 53
  14. 2019In the Wild Human Pose Estimation Using Explicit 2D Features and Intermediate 3D Representationscited by 48
  15. 2020Self-Supervised 3D Human Pose Estimation via Part Guided Novel Image Synthesiscited by 44
  16. 2016Structured Prediction of 3D Human Pose with Deep Neural Networkscited by 43
  17. 2016Deep Kinematic Pose Regressioncited by 40
  18. 2015Maximum-Margin Structured Learning with Deep Networks for 3D Human Pose Estimationcited by 37
  19. 2017Adversarial PoseNet: A Structure-aware Convolutional Network for Human Pose Estimationcited by 35
  20. 2021TransFusion: Cross-view Fusion with Transformer for 3D Human Pose Estimationcited by 32
  21. 2019Multiview-Consistent Semi-Supervised Learning for 3D Human Pose Estimationcited by 31
  22. 2017Deep Multitask Architecture for Integrated 2D and 3D Human Sensingcited by 21
  23. 2022On Triangulation as a Form of Self-Supervision for 3D Human Pose Estimationcited by 10

Built on by

Not cited yet.