# Simple and Lightweight Human Pose Estimation

arXiv: https://arxiv.org/abs/1911.10346 · HTML: https://mlsanity.com/paper/1911.10346/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 23 Nov 2019.

## Built on by (most cited first, 10 of 10)

- [DeciWatch: A Simple Baseline for 10x Efficient 2D and 3D Pose Estimation](https://mlsanity.com/paper/2203.08713/) (2022)
- [HPTQ: Hardware-Friendly Post Training Quantization](https://mlsanity.com/paper/2109.09113/) (2021)
- [Video Based Fall Detection Using Human Poses](https://mlsanity.com/paper/2107.14633/) (2021)
- [Orderly Dual-Teacher Knowledge Distillation for Lightweight Human Pose Estimation](https://mlsanity.com/paper/2104.10414/) (2021)
- [FasterPose: A Faster Simple Baseline for Human Pose Estimation](https://mlsanity.com/paper/2107.03215/) (2021)
- [Efficient, Self-Supervised Human Pose Estimation with Inductive Prior Tuning](https://mlsanity.com/paper/2311.02815/) (2023)
- [Efficient Human Pose Estimation by Maximizing Fusion and High-Level Spatial Attention](https://mlsanity.com/paper/2107.13693/) (2021)
- [Rethinking Deconvolution for 2D Human Pose Estimation Light yet Accurate Model for Real-time Edge Computing](https://mlsanity.com/paper/2111.04226/) (2021)
- [BiHRNet: A Binary high-resolution network for Human Pose Estimation](https://mlsanity.com/paper/2311.10296/) (2023)
- [LAPX: Lightweight Hourglass Network with Global Context](https://mlsanity.com/paper/2512.16089/) (2025)

## Abstract (arXiv)

Recent research on human pose estimation has achieved significant improvement. However, most existing methods tend to pursue higher scores using complex architecture or computationally expensive models on benchmark datasets, ignoring the deployment costs in practice. In this paper, we investigate the problem of simple and lightweight human pose estimation. We first redesign a lightweight bottleneck block with two non-novel concepts: depthwise convolution and attention mechanism. And then, based on the lightweight block, we present a Lightweight Pose Network (LPN) following the architecture design principles of SimpleBaseline. The model size (#Params) of our small network LPN-50 is only 9% of SimpleBaseline(ResNet50), and the computational complexity (FLOPs) is only 11%. To give full play to the potential of our LPN and get more accurate predicted results, we also propose an iterative training strategy and a model-agnostic post-processing function Beta-Soft-Argmax. We empirically demonstrate the effectiveness and efficiency of our methods on the benchmark dataset: the COCO keypoint detection dataset. Besides, we show the speed superiority of our lightweight network at inference time on a non-GPU platform. Specifically, our LPN-50 can achieve 68.7 in AP score on the COCO test-dev set, with only 2.7M parameters and 1.0 GFLOPs, while the inference speed is 17 FPS on an Intel i7-8700K CPU machine.