HYPERPOSE: Hyperbolic Kinematic Phase-Space Attention for 3D Human Pose Estimation

TL;DR

HYPERPOSE introduces a hyperbolic space-based framework for 3D human pose estimation, effectively preserving skeletal hierarchy and improving structural and temporal accuracy over Euclidean-based methods.

Contribution

It pioneers the use of hyperbolic geometry in pose estimation, with a novel attention mechanism and training strategies to enhance structural fidelity and temporal modeling.

Findings

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

Reduces volume distortion and velocity error compared to Euclidean methods.

Establishes new benchmarks in overall positional accuracy.

Abstract

We introduce HYPERPOSE, a novel 3D human pose estimation framework that performs spatio-temporal reasoning entirely within the Lorentz model of hyperbolic space $\mathbb{H}^d$ to natively preserve the hierarchical tree topology of the human skeleton. Current state-of-the-art pose estimators aim to capture complex joint dynamics by relying on transformers and graph convolutional networks. Since these architectures operate exclusively in Euclidean space which fundamentally mismatches the inherent tree structure of the human body, these methods inevitably suffer from exponential volume distortion and struggle to maintain structural coherence. To this end, we depart from flat spaces and aim to improve geometric fidelity with Hyperbolic Kinematic Phase-Space Attention (HKPSA), natively embedding complex joint relationships without distortion, alongside a multi-scale windowed hyperbolic attention mechanism that efficiently models temporal dynamics in $O(TW)$ complexity. Furthermore, to overcome the well-known instability of training non-Euclidean manifolds, HYPERPOSE introduces a novel Riemannian loss suite and an uncertainty-weighted curriculum, enforcing physical geodesic constraints like bone length and velocity consistency. Extensive evaluations on the Human3.6M and MPI-INF-3DHP datasets demonstrate that HYPERPOSE achieves state-of-the-art structural and temporal coherence, significantly reducing both volume distortion and velocity error, while establishing new state-of-the-art benchmarks in overall positional accuracy.