Learning Pose Grammar to Encode Human Body Configuration for 3D Pose Estimation

TL;DR

This paper introduces a pose grammar model that encodes human body configurations to improve 3D pose estimation from 2D inputs, utilizing hierarchical RNNs and a pose sample simulator for better generalization.

Contribution

It presents a novel pose grammar framework with hierarchical RNNs and a virtual sample generator, enhancing 3D pose estimation accuracy and cross-view generalization.

Findings

Outperforms existing methods on public benchmarks.

Effectively handles cross-view pose estimation challenges.

Improves generalization with pose sample augmentation.

Abstract

In this paper, we propose a pose grammar to tackle the problem of 3D human pose estimation. Our model directly takes 2D pose as input and learns a generalized 2D-3D mapping function. The proposed model consists of a base network which efficiently captures pose-aligned features and a hierarchy of Bi-directional RNNs (BRNN) on the top to explicitly incorporate a set of knowledge regarding human body configuration (i.e., kinematics, symmetry, motor coordination). The proposed model thus enforces high-level constraints over human poses. In learning, we develop a pose sample simulator to augment training samples in virtual camera views, which further improves our model generalizability. We validate our method on public 3D human pose benchmarks and propose a new evaluation protocol working on cross-view setting to verify the generalization capability of different methods. We empirically observe that most state-of-the-art methods encounter difficulty under such setting while our method can well handle such challenges.