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

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.

Accepted by AAAI 2018

References in corpus (6)

• Adam: A Method for Stochastic Optimization
• Stacked Hourglass Networks for Human Pose Estimation
• MoCap-guided Data Augmentation for 3D Pose Estimation in the Wild
• A simple yet effective baseline for 3d human pose estimation
• Structured Prediction of 3D Human Pose with Deep Neural Networks
• 3D Human Pose Estimation = 2D Pose Estimation + Matching

Cited by in corpus (4)

• 3D Human Pose Estimation with Relational Networks
• HybrIK: A Hybrid Analytical-Neural Inverse Kinematics Solution for 3D Human Pose and Shape Estimation
• Deep Monocular 3D Human Pose Estimation via Cascaded Dimension-Lifting
• 3D Human Pose Estimation Based on 2D-3D Consistency with Synchronized Adversarial Training