SOTAVerified

RMPE: Regional Multi-person Pose Estimation

2016-12-01ICCV 2017Code Available3· sign in to hype

Hao-Shu Fang, Shuqin Xie, Yu-Wing Tai, Cewu Lu

arXivPDF

Code Available — Be the first to reproduce this paper.

Reproduce

Code

Abstract

Multi-person pose estimation in the wild is challenging. Although state-of-the-art human detectors have demonstrated good performance, small errors in localization and recognition are inevitable. These errors can cause failures for a single-person pose estimator (SPPE), especially for methods that solely depend on human detection results. In this paper, we propose a novel regional multi-person pose estimation (RMPE) framework to facilitate pose estimation in the presence of inaccurate human bounding boxes. Our framework consists of three components: Symmetric Spatial Transformer Network (SSTN), Parametric Pose Non-Maximum-Suppression (NMS), and Pose-Guided Proposals Generator (PGPG). Our method is able to handle inaccurate bounding boxes and redundant detections, allowing it to achieve a 17% increase in mAP over the state-of-the-art methods on the MPII (multi person) dataset.Our model and source codes are publicly available.

Tasks

2D Human Pose EstimationHuman DetectionKeypoint DetectionMulti-Person Pose EstimationPose Estimation

Benchmark Results

DatasetModelMetricClaimedVerifiedStatus
CrowdPoseAlphaPosemAP @0.5:0.9561—Unverified
MPII Multi-PersonAlphaPoseAP82.1—Unverified

Reproductions