Stacked Hourglass Networks for Human Pose Estimation

TL;DR

This paper introduces a stacked hourglass convolutional network architecture that processes features across multiple scales with repeated bottom-up and top-down steps, significantly improving human pose estimation accuracy.

Contribution

The novel stacked hourglass network architecture effectively captures multi-scale features for human pose estimation, outperforming previous methods on standard benchmarks.

Findings

Achieved state-of-the-art results on FLIC and MPII datasets.

Demonstrated the importance of multi-scale feature processing and intermediate supervision.

Outperformed recent methods in human pose estimation accuracy.

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.