Stacked Hourglass Networks for Human Pose Estimation

03/22/2016 ∙ by Alejandro Newell, et al. ∙ 0

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.

READ FULL TEXT

Authors

page 3

page 8

page 11

page 12

Code Repositories

pose-hg-train

Training and experimentation code used for "Stacked Hourglass Networks for Human Pose Estimation"


view repo

pose-hg-demo

Code to test and use the model from "Stacked Hourglass Networks for Human Pose Estimation"


view repo

hourglass-facekeypoints-detection

face keypoints deteciton based on stackedhourglass


view repo

stacked-hourglass

Our modification of the stacked-hourglass architecture for car keypoint localization


view repo
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.