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

arXiv: https://arxiv.org/abs/2205.01271 · HTML: https://mlsanity.com/paper/2205.01271/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- Builds on 53 of its 60 references that are in the map.
- First posted on arXiv 3 May 2022.

## Builds on (most cited first, 30 of 53)

- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [MobileNetV2: Inverted Residuals and Linear Bottlenecks](https://mlsanity.com/paper/1801.04381/) (2018)
- [MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications](https://mlsanity.com/paper/1704.04861/) (2017)
- [Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding](https://mlsanity.com/paper/1510.00149/) (2015)
- [Learning both Weights and Connections for Efficient Neural Networks](https://mlsanity.com/paper/1506.02626/) (2015)
- [Searching for MobileNetV3](https://mlsanity.com/paper/1905.02244/) (2019)
- [DARTS: Differentiable Architecture Search](https://mlsanity.com/paper/1806.09055/) (2018)
- [Neural Architecture Search with Reinforcement Learning](https://mlsanity.com/paper/1611.01578/) (2016)
- [Deep High-Resolution Representation Learning for Human Pose Estimation](https://mlsanity.com/paper/1902.09212/) (2019)
- [ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices](https://mlsanity.com/paper/1707.01083/) (2017)
- [OpenPose: Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields](https://mlsanity.com/paper/1812.08008/) (2018)
- [ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design](https://mlsanity.com/paper/1807.11164/) (2018)
- [Stacked Hourglass Networks for Human Pose Estimation](https://mlsanity.com/paper/1603.06937/) (2016)
- [Regularized Evolution for Image Classifier Architecture Search](https://mlsanity.com/paper/1802.01548/) (2018)
- [Once-for-All: Train One Network and Specialize it for Efficient Deployment](https://mlsanity.com/paper/1908.09791/) (2019)
- [Channel Pruning for Accelerating Very Deep Neural Networks](https://mlsanity.com/paper/1707.06168/) (2017)
- [Learning Efficient Convolutional Networks through Network Slimming](https://mlsanity.com/paper/1708.06519/) (2017)
- [ProxylessNAS: Direct Neural Architecture Search on Target Task and Hardware](https://mlsanity.com/paper/1812.00332/) (2018)
- [Learning Structured Sparsity in Deep Neural Networks](https://mlsanity.com/paper/1608.03665/) (2016)
- [Quantizing deep convolutional networks for efficient inference: A whitepaper](https://mlsanity.com/paper/1806.08342/) (2018)
- [Simple Baselines for Human Pose Estimation and Tracking](https://mlsanity.com/paper/1804.06208/) (2018)
- [Progressive Neural Architecture Search](https://mlsanity.com/paper/1712.00559/) (2017)
- [FBNet: Hardware-Aware Efficient ConvNet Design via Differentiable Neural Architecture Search](https://mlsanity.com/paper/1812.03443/) (2018)
- [HAQ: Hardware-Aware Automated Quantization with Mixed Precision](https://mlsanity.com/paper/1811.08886/) (2018)
- [Bag of Tricks for Image Classification with Convolutional Neural Networks](https://mlsanity.com/paper/1812.01187/) (2018)
- [Single Path One-Shot Neural Architecture Search with Uniform Sampling](https://mlsanity.com/paper/1904.00420/) (2019)
- [AMC: AutoML for Model Compression and Acceleration on Mobile Devices](https://mlsanity.com/paper/1802.03494/) (2018)
- [Point-Voxel CNN for Efficient 3D Deep Learning](https://mlsanity.com/paper/1907.03739/) (2019)

## Built on by (most cited first, 16 of 16)

- [Human Pose as Compositional Tokens](https://mlsanity.com/paper/2303.11638/) (2023)
- [EfficientViT: Multi-Scale Linear Attention for High-Resolution Dense Prediction](https://mlsanity.com/paper/2205.14756/) (2022)
- [PPT: token-Pruned Pose Transformer for monocular and multi-view human pose estimation](https://mlsanity.com/paper/2209.08194/) (2022)
- [JAWS: Just A Wild Shot for Cinematic Transfer in Neural Radiance Fields](https://mlsanity.com/paper/2303.15427/) (2023)
- [GTPT: Group-based Token Pruning Transformer for Efficient Human Pose Estimation](https://mlsanity.com/paper/2407.10756/) (2024)
- [Occluded Human Pose Estimation based on Limb Joint Augmentation](https://mlsanity.com/paper/2410.09885/) (2024)
- [Geometric Visual Fusion Graph Neural Networks for Multi-Person Human-Object Interaction Recognition in Videos](https://mlsanity.com/paper/2506.03440/) (2025)
- [Binarizing by Classification: Is soft function really necessary?](https://mlsanity.com/paper/2205.07433/) (2022)
- [Waterfall Transformer for Multi-person Pose Estimation](https://mlsanity.com/paper/2411.18944/) (2024)
- [Global Relation Modeling and Refinement for Bottom-Up Human Pose Estimation](https://mlsanity.com/paper/2303.14888/) (2023)
- [A Spatial-Temporal Transformer based Framework For Human Pose Assessment And Correction in Education Scenarios](https://mlsanity.com/paper/2311.00401/) (2023)
- [Cross-Domain Knowledge Distillation for Low-Resolution Human Pose Estimation](https://mlsanity.com/paper/2405.11448/) (2024)
- [Greit-HRNet: Grouped Lightweight High-Resolution Network for Human Pose Estimation](https://mlsanity.com/paper/2407.07389/) (2024)
- [Cascaded Multi-Scale Attention for Enhanced Multi-Scale Feature Extraction and Interaction with Low-Resolution Images](https://mlsanity.com/paper/2412.02197/) (2024)
- [ProARD: progressive adversarial robustness distillation: provide wide range of robust students](https://mlsanity.com/paper/2506.07666/) (2025)
- [On the Use of Hierarchical Vision Foundation Models for Low-Cost Human Mesh Recovery and Pose Estimation](https://mlsanity.com/paper/2510.12660/) (2025)

## Abstract (arXiv)

Pose estimation plays a critical role in human-centered vision applications. However, it is difficult to deploy state-of-the-art HRNet-based pose estimation models on resource-constrained 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 multi-person 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 Convs. Fusion Deconv Head removes the redundancy in high-resolution branches, allowing scale-aware feature fusion with low overhead. Large Kernel Convs significantly improve the model's capacity and receptive field while maintaining a low computational cost. With only 25% computation increment, 7x7 kernels achieve +14.0 mAP better than 3x3 kernels on the CrowdPose dataset. On mobile platforms, LitePose reduces the latency by up to 5.0x 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.