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

TL;DR

This paper introduces PoseKAN, an adaptive graph Kolmogorov-Arnold Network for 3D human pose estimation that enhances long-range dependency modeling and feature expressiveness over traditional GCNs.

Contribution

The paper proposes a novel PoseKAN framework with learnable edge functions, multi-hop aggregation, and residual blocks, improving 3D pose estimation accuracy and robustness.

Findings

Achieves competitive results on benchmark datasets.

Outperforms existing GCN-based methods in handling occlusions.

Demonstrates improved modeling of complex pose variations.

Abstract

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.