mlsanityData to 14 Oct 2026

Adaptive graph Kolmogorov-Arnold network for 3D human pose estimation

arXiv 2511.08809 ↗First posted 11 Nov 2025cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Graph convolutional network (GCN)-based methods have shown strong performance in 3D human pose estimation by leveraging the natural graph structure of the human skeleton. However, their local receptive field limits their ability to capture long-range dependencies essential for handling occlusions and depth ambiguities. They also exhibit spectral bias, which prioritizes low-frequency components while struggling to model high-frequency details. In this paper, we introduce PoseKAN, an adaptive graph Kolmogorov-Arnold Network (KAN), framework that extends KANs to graph-based learning for 2D-to-3D pose lifting from a single image. Unlike GCNs that use fixed activation functions, KANs employ learnable functions on graph edges, allowing data-driven, adaptive feature transformations. This enhances the model's adaptability and expressiveness, making it more expressive in learning complex pose variations. Our model employs multi-hop feature aggregation, ensuring the body joints can leverage information from both local and distant neighbors, leading to improved spatial awareness. It also incorporates residual PoseKAN blocks for deeper feature refinement, and a global response normalization for improved feature selectivity and contrast. Extensive experiments on benchmark datasets demonstrate the competitive performance of our model against state-of-the-art methods.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 27 of its 45 references that are in the map. First posted on arXiv 11 Nov 2025.

Builds on

27 of 45 references.

References · 27

  1. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
  2. 2018On the Spectral Bias of Neural Networkscited by 1,341
  3. 2023ConvNeXt V2: Co-designing and Scaling ConvNets with Masked Autoencoderscited by 712
  4. 2024KAN: Kolmogorov-Arnold Networkscited by 649
  5. 2016Monocular 3D Human Pose Estimation In The Wild Using Improved CNN Supervisioncited by 494
  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. 2017Integral Human Pose Regressioncited by 256
  9. 2016Coarse-to-Fine Volumetric Prediction for Single-Image 3D Human Posecited by 221
  10. 2019Semantic Graph Convolutional Networks for 3D Human Pose Regressioncited by 204
  11. 2017Compositional Human Pose Regressioncited by 124
  12. 2018Ordinal Depth Supervision for 3D Human Pose Estimationcited by 107
15 more
  1. 2021Graph Stacked Hourglass Networks for 3D Human Pose Estimationcited by 95
  2. 2020SRNet: Improving Generalization in 3D Human Pose Estimation with a Split-and-Recombine Approachcited by 94
  3. 2020The Kolmogorov-Arnold representation theorem revisitedcited by 89
  4. 2019Monocular 3D Human Pose Estimation by Generation and Ordinal Rankingcited by 76
  5. 2021Learning Skeletal Graph Neural Networks for Hard 3D Pose Estimationcited by 62
  6. 2019HEMlets Pose: Learning Part-Centric Heatmap Triplets for Accurate 3D Human Pose Estimationcited by 50
  7. 2024KAGNNs: Kolmogorov-Arnold Networks meet Graph Learningcited by 49
  8. 2024On the expressiveness and spectral bias of KANscited by 37
  9. 20163D Human Pose Estimation Using Convolutional Neural Networks with 2D Pose Informationcited by 28
  10. 2020Weakly Supervised Generative Network for Multiple 3D Human Pose Hypothesescited by 25
  11. 2022GraphMLP: A Graph MLP-Like Architecture for 3D Human Pose Estimationcited by 21
  12. 2019Not All Parts Are Created Equal: 3D Pose Estimation by Modelling Bi-directional Dependencies of Body Partscited by 19
  13. 20213D Human Pose Regression using Graph Convolutional Networkcited by 8
  14. 2021Higher-Order Implicit Fairing Networks for 3D Human Pose Estimationcited by 8
  15. 2024Flexible graph convolutional network for 3D human pose estimationcited by 1

Built on by

Not cited yet.