# Seeing Through WiFi: Lightweight Human Pose Estimation with Dynamic Kernel Attention

arXiv: https://arxiv.org/abs/2607.03196 · HTML: https://mlsanity.com/paper/2607.03196/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 12 of its 58 references that are in the map.
- First posted on arXiv 3 Jul 2026.

## Builds on (most cited first, 12 of 12)

- [Squeeze-and-Excitation Networks](https://mlsanity.com/paper/1709.01507/) (2017)
- [OpenPose: Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields](https://mlsanity.com/paper/1812.08008/) (2018)
- [Selective Kernel Networks](https://mlsanity.com/paper/1903.06586/) (2019)
- [Dynamic Convolution: Attention over Convolution Kernels](https://mlsanity.com/paper/1912.03458/) (2019)
- [RMPE: Regional Multi-person Pose Estimation](https://mlsanity.com/paper/1612.00137/) (2016)
- [MM-Fi: Multi-Modal Non-Intrusive 4D Human Dataset for Versatile Wireless Sensing](https://mlsanity.com/paper/2305.10345/) (2023)
- [Omni-Dimensional Dynamic Convolution](https://mlsanity.com/paper/2209.07947/) (2022)
- [Frequency Dynamic Convolution: Frequency-Adaptive Pattern Recognition for Sound Event Detection](https://mlsanity.com/paper/2203.15296/) (2022)
- [MetaFi: Device-Free Pose Estimation via Commodity WiFi for Metaverse Avatar Simulation](https://mlsanity.com/paper/2208.10414/) (2022)
- [Can WiFi Estimate Person Pose?](https://mlsanity.com/paper/1904.00277/) (2019)
- [From Point to Space: 3D Moving Human Pose Estimation Using Commodity WiFi](https://mlsanity.com/paper/2012.14066/) (2020)
- [TinySense: Effective CSI Compression for Scalable and Accurate Wi-Fi Sensing](https://mlsanity.com/paper/2601.15838/) (2026)

## Abstract (arXiv)

WiFi-based human pose estimation (HPE) enables the detection and interpretation of human body positions and movements without the need for wearable devices while preserving individual privacy concerns. Implementing this solution requires enhancing model performance and maintaining efficiency, especially on resource-constrained devices. This paper introduces a novel framework, WiLHPE, for lightweight and efficient human pose estimation using WiFi CSI signals. Empowered by a camera-based model during training, WiLHPE processes raw WiFi signals directly to estimate human poses in the testing phase. It employs a novel neural network architecture to dynamically learn convolutional kernels and apply attention mechanisms across channel and frequency spaces. This innovative method diversifies the kernels to improve the recognition capabilities of WiFi signals without adding complexity, ensuring efficiency. Additionally, the Tree-Structured Parzen Estimator algorithm is employed to optimize the critical hyperparameters of the neural network efficiently, minimizing the time required for optimal hyperparameter search compared to heuristic methods. Results from experiments on both the MM-Fi and WiPose datasets highlight the superiority of WiLHPE over state-of-the-art approaches, achieving 85.96% and 94.27% at PCK50, respectively, with minimal computational overhead. Notably, WiLHPE performs impressively even under challenging conditions, maintaining around 80% at PCK50 under AWGN noise with an error variance of 0.5.