SOTAVerified

Stacked Hourglass Networks for Human Pose Estimation

2016-03-22Code Available1· sign in to hype

Alejandro Newell, Kaiyu Yang, Jia Deng

arXivPDF

Code Available — Be the first to reproduce this paper.

Reproduce

Code

Abstract

This work introduces a novel convolutional network architecture for the task of human pose estimation. Features are processed across all scales and consolidated to best capture the various spatial relationships associated with the body. We show how repeated bottom-up, top-down processing used in conjunction with intermediate supervision is critical to improving the performance of the network. We refer to the architecture as a "stacked hourglass" network based on the successive steps of pooling and upsampling that are done to produce a final set of predictions. State-of-the-art results are achieved on the FLIC and MPII benchmarks outcompeting all recent methods.

Tasks

Pose Estimation

Benchmark Results

DatasetModelMetricClaimedVerifiedStatus
FLIC ElbowsStacked Hourglass NetworksPCK@0.299—Unverified
FLIC WristsStacked Hourglass NetworksPCK@0.297—Unverified
MPII Human PoseStacked Hourglass NetworksPCKh-0.590.9—Unverified

Reproductions