3D Human Pose Estimation Using M\"obius Graph Convolutional Networks

TL;DR

This paper introduces M"obiusGCN, a spectral graph convolutional network that explicitly encodes joint transformations for 3D human pose estimation, achieving state-of-the-art accuracy with significantly fewer parameters.

Contribution

The paper proposes a novel M"obius transformation-based spectral GCN that explicitly models joint transformations, reducing parameters and improving performance in 3D human pose estimation.

Findings

Achieves state-of-the-art results on Human3.6M and MPI-INF-3DHP datasets.

Uses 90-98% fewer parameters than previous models.

Demonstrates strong generalization capabilities.

Abstract

3D human pose estimation is fundamental to understanding human behavior. Recently, promising results have been achieved by graph convolutional networks (GCNs), which achieve state-of-the-art performance and provide rather light-weight architectures. However, a major limitation of GCNs is their inability to encode all the transformations between joints explicitly. To address this issue, we propose a novel spectral GCN using the M\"obius transformation (M\"obiusGCN). In particular, this allows us to directly and explicitly encode the transformation between joints, resulting in a significantly more compact representation. Compared to even the lightest architectures so far, our novel approach requires 90-98% fewer parameters, i.e. our lightest M\"obiusGCN uses only 0.042M trainable parameters. Besides the drastic parameter reduction, explicitly encoding the transformation of joints also enables us to achieve state-of-the-art results. We evaluate our approach on the two challenging pose estimation benchmarks, Human3.6M and MPI-INF-3DHP, demonstrating both state-of-the-art results and the generalization capabilities of M\"obiusGCN.