Adaptive graph Kolmogorov-Arnold network for 3D human pose estimation
By: Abu Taib Mohammed Shahjahan, A. Ben Hamza
Potential Business Impact:
Helps computers guess body poses from pictures.
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.
Similar Papers
Transferring Social Network Knowledge from Multiple GNN Teachers to Kolmogorov-Arnold Networks
Machine Learning (CS)
Makes AI learn faster without needing all the connections.
LuKAN: A Kolmogorov-Arnold Network Framework for 3D Human Motion Prediction
CV and Pattern Recognition
Predicts future body movements more accurately and faster.
TrafficKAN-GCN: Graph Convolutional-based Kolmogorov-Arnold Network for Traffic Flow Optimization
Machine Learning (CS)
Makes traffic lights smarter to stop jams.