SIMPLE: SIngle-network with Mimicking and Point Learning for Bottom-up Human Pose Estimation

TL;DR

SIMPLE is a novel bottom-up human pose estimation framework that mimics top-down knowledge and unifies detection and pose estimation in a single network, achieving state-of-the-art results with high efficiency.

Contribution

The paper introduces the first mimicking strategy between top-down and bottom-up methods and a unified point learning framework for pose estimation.

Findings

Achieves state-of-the-art performance among bottom-up methods on COCO, MPII, and PoseTrack datasets.

Maintains high inference speed comparable to top-down methods.

Outperforms previous bottom-up approaches in accuracy.

Abstract

The practical application requests both accuracy and efficiency on multi-person pose estimation algorithms. But the high accuracy and fast inference speed are dominated by top-down methods and bottom-up methods respectively. To make a better trade-off between accuracy and efficiency, we propose a novel multi-person pose estimation framework, SIngle-network with Mimicking and Point Learning for Bottom-up Human Pose Estimation (SIMPLE). Specifically, in the training process, we enable SIMPLE to mimic the pose knowledge from the high-performance top-down pipeline, which significantly promotes SIMPLE's accuracy while maintaining its high efficiency during inference. Besides, SIMPLE formulates human detection and pose estimation as a unified point learning framework to complement each other in single-network. This is quite different from previous works where the two tasks may interfere with each other. To the best of our knowledge, both mimicking strategy between different method types and unified point learning are firstly proposed in pose estimation. In experiments, our approach achieves the new state-of-the-art performance among bottom-up methods on the COCO, MPII and PoseTrack datasets. Compared with the top-down approaches, SIMPLE has comparable accuracy and faster inference speed.