Lite Pose: Efficient Architecture Design for 2D Human Pose Estimation

Yihan Wang, Muyang Li, Han Cai, Wei-Ming Chen, Song Han

Abstract:

Pose estimation plays a critical role in human-centered
vision applications. However, it is difficult to deploy stateof-the-art HRNet-based pose estimation models on resourceconstrained edge devices due to the high computational
cost (more than 150 GMACs per frame). In this paper,
we study efficient architecture design for real-time multiperson pose estimation on edge. We reveal that HRNet’s
high-resolution branches are redundant for models at the
low-computation region via our gradual shrinking experiments. Removing them improves both efficiency and performance. Inspired by this finding, we design LitePose, an
efficient single-branch architecture for pose estimation, and
introduce two simple approaches to enhance the capacity
of LitePose, including fusion deconv head and large kernel
conv. On mobile platforms, LitePose reduces the latency by
up to 5.0× without sacrificing performance, compared with
prior state-of-the-art efficient pose estimation models, pushing the frontier of real-time multi-person pose estimation
on edge. Our code and pre-trained models are released at
https://github.com/mit-han-lab/litepose.