mlsanityData to 7 Oct 2026

Learning Pyramid-structured Long-range Dependencies for 3D Human Pose Estimation

arXiv 2506.02853 ↗First posted 3 Jun 2025cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Action coordination in human structure is indispensable for the spatial constraints of 2D joints to recover 3D pose. Usually, action coordination is represented as a long-range dependence among body parts. However, there are two main challenges in modeling long-range dependencies. First, joints should not only be constrained by other individual joints but also be modulated by the body parts. Second, existing methods make networks deeper to learn dependencies between non-linked parts. They introduce uncorrelated noise and increase the model size. In this paper, we utilize a pyramid structure to better learn potential long-range dependencies. It can capture the correlation across joints and groups, which complements the context of the human sub-structure. In an effective cross-scale way, it captures the pyramid-structured long-range dependence. Specifically, we propose a novel Pyramid Graph Attention (PGA) module to capture long-range cross-scale dependencies. It concatenates information from various scales into a compact sequence, and then computes the correlation between scales in parallel. Combining PGA with graph convolution modules, we develop a Pyramid Graph Transformer (PGFormer) for 3D human pose estimation, which is a lightweight multi-scale transformer architecture. It encapsulates human sub-structures into self-attention by pooling. Extensive experiments show that our approach achieves lower error and smaller model size than state-of-the-art methods on Human3.6M and MPI-INF-3DHP datasets. The code is available at https://github.com/MingjieWe/PGFormer.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 37 of its 63 references that are in the map. First posted on arXiv 3 Jun 2025.

Builds on

37 of 63 references.

References · 37

  1. 2017Attention Is All You Needcited by 59,932
  2. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  3. 2020Denoising Diffusion Implicit Modelscited by 9,655
  4. 2017Graph Attention Networkscited by 8,854
  5. 2016Feature Pyramid Networks for Object Detectioncited by 5,021
  6. 2017Non-local Neural Networkscited by 2,290
  7. 2016Convolutional Neural Networks on Graphs with Fast Localized Spectral Filteringcited by 2,085
  8. 2021Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutionscited by 1,960
  9. 2016Monocular 3D Human Pose Estimation In The Wild Using Improved CNN Supervisioncited by 493
  10. 2019Self-Attention Graph Poolingcited by 421
  11. 2017A simple yet effective baseline for 3d human pose estimationcited by 401
  12. 20183D human pose estimation in video with temporal convolutions and semi-supervised trainingcited by 401
25 more
  1. 20213D Human Pose Estimation with Spatial and Temporal Transformerscited by 271
  2. 2016Coarse-to-Fine Volumetric Prediction for Single-Image 3D Human Posecited by 220
  3. 2019Semantic Graph Convolutional Networks for 3D Human Pose Regressioncited by 204
  4. 2022MixSTE: Seq2seq Mixed Spatio-Temporal Encoder for 3D Human Pose Estimation in Videocited by 158
  5. 2021MHFormer: Multi-Hypothesis Transformer for 3D Human Pose Estimationcited by 151
  6. 2017Towards 3D Human Pose Estimation in the Wild: a Weakly-supervised Approachcited by 114
  7. 2022DiffPose: Toward More Reliable 3D Pose Estimationcited by 99
  8. 2020SRNet: Improving Generalization in 3D Human Pose Estimation with a Split-and-Recombine Approachcited by 94
  9. 2021Exploiting Temporal Contexts with Strided Transformer for 3D Human Pose Estimationcited by 94
  10. 2021Graph Stacked Hourglass Networks for 3D Human Pose Estimationcited by 94
  11. 2021PoseAug: A Differentiable Pose Augmentation Framework for 3D Human Pose Estimationcited by 88
  12. 20183D Human Pose Estimation in the Wild by Adversarial Learningcited by 86
  13. 2020Motion Guided 3D Pose Estimation from Videoscited by 85
  14. 2021P2T: Pyramid Pooling Transformer for Scene Understandingcited by 84
  15. 2019Monocular 3D Human Pose Estimation by Generation and Ordinal Rankingcited by 76
  16. 2022DiffPose: Multi-hypothesis Human Pose Estimation using Diffusion modelscited by 65
  17. 2021Learning Skeletal Graph Neural Networks for Hard 3D Pose Estimationcited by 62
  18. 2021Conditional Directed Graph Convolution for 3D Human Pose Estimationcited by 52
  19. 2019HEMlets Pose: Learning Part-Centric Heatmap Triplets for Accurate 3D Human Pose Estimationcited by 50
  20. 2023Implicit Temporal Modeling with Learnable Alignment for Video Recognitioncited by 44
  21. 2020Path Integral Based Convolution and Pooling for Graph Neural Networkscited by 35
  22. 2023HDFormer: High-order Directed Transformer for 3D Human Pose Estimationcited by 23
  23. 2021Weakly-supervised 3D Human Pose Estimation with Cross-view U-shaped Graph Convolutional Networkcited by 13
  24. 2023PoSynDA: Multi-Hypothesis Pose Synthesis Domain Adaptation for Robust 3D Human Pose Estimationcited by 12
  25. 2023Skeleton-based Action Recognition through Contrasting Two-Stream Spatial-Temporal Networkscited by 9

Built on by

Not cited yet.