Single-Stage Multi-Person Pose Machines

TL;DR

This paper introduces a novel single-stage model, SPM, for multi-person pose estimation that unifies person and joint representations, significantly improving efficiency while maintaining high accuracy.

Contribution

The paper proposes the first single-stage multi-person pose estimation model using Structured Pose Representation, simplifying the pipeline and enhancing efficiency over traditional two-stage methods.

Findings

Achieves state-of-the-art efficiency on multiple benchmarks.

Demonstrates high accuracy in 2D and 3D multi-person pose estimation.

Validates the generality of SPM across different datasets.

Abstract

Multi-person pose estimation is a challenging problem. Existing methods are mostly two-stage based--one stage for proposal generation and the other for allocating poses to corresponding persons. However, such two-stage methods generally suffer low efficiency. In this work, we present the first single-stage model, Single-stage multi-person Pose Machine (SPM), to simplify the pipeline and lift the efficiency for multi-person pose estimation. To achieve this, we propose a novel Structured Pose Representation (SPR) that unifies person instance and body joint position representations. Based on SPR, we develop the SPM model that can directly predict structured poses for multiple persons in a single stage, and thus offer a more compact pipeline and attractive efficiency advantage over two-stage methods. In particular, SPR introduces the root joints to indicate different person instances and human body joint positions are encoded into their displacements w.r.t. the roots. To better predict long-range displacements for some joints, SPR is further extended to hierarchical representations. Based on SPR, SPM can efficiently perform multi-person poses estimation by simultaneously predicting root joints (location of instances) and body joint displacements via CNNs. Moreover, to demonstrate the generality of SPM, we also apply it to multi-person 3D pose estimation. Comprehensive experiments on benchmarks MPII, extended PASCAL-Person-Part, MSCOCO and CMU Panoptic clearly demonstrate the state-of-the-art efficiency of SPM for multi-person 2D/3D pose estimation, together with outstanding accuracy.