LuKAN: A Kolmogorov-Arnold Network Framework for 3D Human Motion Prediction

TL;DR

LuKAN is a novel 3D human motion prediction model that combines wavelet transforms, Lucas polynomial-based Kolmogorov-Arnold Networks, and a spatial projection layer to achieve accurate and efficient predictions.

Contribution

The paper introduces LuKAN, a new model using Kolmogorov-Arnold Networks with Lucas polynomials for improved efficiency and accuracy in 3D human motion prediction.

Findings

Competitive performance on benchmark datasets

High computational efficiency due to linear recurrence

Effective modeling of oscillatory motion behaviors

Abstract

The goal of 3D human motion prediction is to forecast future 3D poses of the human body based on historical motion data. Existing methods often face limitations in achieving a balance between prediction accuracy and computational efficiency. In this paper, we present LuKAN, an effective model based on Kolmogorov-Arnold Networks (KANs) with Lucas polynomial activations. Our model first applies the discrete wavelet transform to encode temporal information in the input motion sequence. Then, a spatial projection layer is used to capture inter-joint dependencies, ensuring structural consistency of the human body. At the core of LuKAN is the Temporal Dependency Learner, which employs a KAN layer parameterized by Lucas polynomials for efficient function approximation. These polynomials provide computational efficiency and an enhanced capability to handle oscillatory behaviors. Finally, the inverse discrete wavelet transform reconstructs motion sequences in the time domain, generating temporally coherent predictions. Extensive experiments on three benchmark datasets demonstrate the competitive performance of our model compared to strong baselines, as evidenced by both quantitative and qualitative evaluations. Moreover, its compact architecture coupled with the linear recurrence of Lucas polynomials, ensures computational efficiency.