mlsanityData to 14 Oct 2026

DeProPose: Deficiency-Proof 3D Human Pose Estimation via Adaptive Multi-View Fusion

arXiv 2502.16419 ↗First posted 23 Feb 2025cs.CV cs.RO eess.IVcited by 0

Not on the map. Why?

Abstract (arXiv)

3D human pose estimation has wide applications in fields such as intelligent surveillance, motion capture, and virtual reality. However, in real-world scenarios, issues such as occlusion, noise interference, and missing viewpoints can severely affect pose estimation. To address these challenges, we introduce the task of Deficiency-Aware 3D Pose Estimation. Traditional 3D pose estimation methods often rely on multi-stage networks and modular combinations, which can lead to cumulative errors and increased training complexity, making them unable to effectively address deficiency-aware estimation. To this end, we propose DeProPose, a flexible method that simplifies the network architecture to reduce training complexity and avoid information loss in multi-stage designs. Additionally, the model innovatively introduces a multi-view feature fusion mechanism based on relative projection error, which effectively utilizes information from multiple viewpoints and dynamically assigns weights, enabling efficient integration and enhanced robustness to overcome deficiency-aware 3D Pose Estimation challenges. Furthermore, to thoroughly evaluate this end-to-end multi-view 3D human pose estimation model and to advance research on occlusion-related challenges, we have developed a novel 3D human pose estimation dataset, termed the Deficiency-Aware 3D Pose Estimation (DA-3DPE) dataset. This dataset encompasses a wide range of deficiency scenarios, including noise interference, missing viewpoints, and occlusion challenges. Compared to state-of-the-art methods, DeProPose not only excels in addressing the deficiency-aware problem but also shows improvement in conventional scenarios, providing a powerful and user-friendly solution for 3D human pose estimation. The source code will be available at https://github.com/WUJINHUAN/DeProPose.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 29 of its 55 references that are in the map. First posted on arXiv 23 Feb 2025.

Builds on

29 of 55 references.

References · 29

  1. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  3. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,139
  4. 2018Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognitioncited by 1,209
  5. 2017A simple yet effective baseline for 3d human pose estimationcited by 401
  6. 20213D Human Pose Estimation with Spatial and Temporal Transformerscited by 272
  7. 2016Coarse-to-Fine Volumetric Prediction for Single-Image 3D Human Posecited by 221
  8. 2020Deep Learning-Based Human Pose Estimation: A Surveycited by 207
  9. 2019Learnable Triangulation of Human Posecited by 161
  10. 2021Deep Occlusion-Aware Instance Segmentation with Overlapping BiLayerscited by 104
  11. 2020SRNet: Improving Generalization in 3D Human Pose Estimation with a Split-and-Recombine Approachcited by 94
  12. 2019Cross View Fusion for 3D Human Pose Estimationcited by 90
17 more
  1. 2020Motion Guided 3D Pose Estimation from Videoscited by 85
  2. 20163D Human Pose Estimation from a Single Image via Distance Matrix Regressioncited by 73
  3. 2021Direct Multi-view Multi-person 3D Pose Estimationcited by 64
  4. 20203D Human Pose Estimation using Spatio-Temporal Networks with Explicit Occlusion Trainingcited by 54
  5. 2019Learning 3D Human Shape and Pose from Dense Body Partscited by 48
  6. 2021Graph-Based 3D Multi-Person Pose Estimation Using Multi-View Imagescited by 38
  7. 20233D-Aware Neural Body Fitting for Occlusion Robust 3D Human Pose Estimationcited by 28
  8. 2018A generalizable approach for multi-view 3D human pose regressioncited by 26
  9. 2021Generalizable Human Pose Triangulationcited by 24
  10. 2018How Robust is 3D Human Pose Estimation to Occlusion?cited by 23
  11. 2024SelfPose3d: Self-Supervised Multi-Person Multi-View 3d Pose Estimationcited by 21
  12. 2021Adaptive Multi-view and Temporal Fusing Transformer for 3D Human Pose Estimationcited by 19
  13. 2017A Multi-view RGB-D Approach for Human Pose Estimation in Operating Roomscited by 17
  14. 2022YOLO-FaceV2: A Scale and Occlusion Aware Face Detectorcited by 15
  15. 2020Self-Supervised Multi-View Synchronization Learning for 3D Pose Estimationcited by 9
  16. 2023Probabilistic Triangulation for Uncalibrated Multi-View 3D Human Pose Estimationcited by 7
  17. 2023View Consistency Aware Holistic Triangulation for 3D Human Pose Estimationcited by 6

Built on by

Not cited yet.