# Reconstructing Depth Images of Moving Objects from Wi-Fi CSI Data

arXiv: https://arxiv.org/abs/2503.06458 · HTML: https://mlsanity.com/paper/2503.06458/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 38 references that are in the map.
- First posted on arXiv 9 Mar 2025.

## Builds on (most cited first, 9 of 9)

- [DensePose: Dense Human Pose Estimation In The Wild](https://mlsanity.com/paper/1802.00434/) (2018)
- [IoU Loss for 2D/3D Object Detection](https://mlsanity.com/paper/1908.03851/) (2019)
- [Person-in-WiFi: Fine-grained Person Perception using WiFi](https://mlsanity.com/paper/1904.00276/) (2019)
- [DensePose From WiFi](https://mlsanity.com/paper/2301.00250/) (2022)
- [Decimeter Ranging with Channel State Information](https://mlsanity.com/paper/1902.09652/) (2019)
- [Wi2Vi: Generating Video Frames from WiFi CSI Samples](https://mlsanity.com/paper/2001.05842/) (2019)
- [CSI2Image: Image Reconstruction from Channel State Information Using Generative Adversarial Networks](https://mlsanity.com/paper/2009.07100/) (2020)
- [Wi-Fi Sensing: Applications and Challenges](https://mlsanity.com/paper/1901.00715/) (2019)
- [High-Resolution WiFi Imaging with Reconfigurable Intelligent Surfaces](https://mlsanity.com/paper/2112.00242/) (2021)

## Built on by (most cited first, 1 of 1)

- [Generative AI Meets Wireless Sensing: Towards Wireless Foundation Model](https://mlsanity.com/paper/2509.15258/) (2025)

## Abstract (arXiv)

This study proposes a new deep learning method for reconstructing depth images of moving objects within a specific area using Wi-Fi channel state information (CSI). The Wi-Fi-based depth imaging technique has novel applications in domains such as security and elder care. However, reconstructing depth images from CSI is challenging because learning the mapping function between CSI and depth images, both of which are high-dimensional data, is particularly difficult. To address the challenge, we propose a new approach called Wi-Depth. The main idea behind the design of Wi-Depth is that a depth image of a moving object can be decomposed into three core components: the shape, depth, and position of the target. Therefore, in the depth-image reconstruction task, Wi-Depth simultaneously estimates the three core pieces of information as auxiliary tasks in our proposed VAE-based teacher-student architecture, enabling it to output images with the consistency of a correct shape, depth, and position. In addition, the design of Wi-Depth is based on our idea that this decomposition efficiently takes advantage of the fact that shape, depth, and position relate to primitive information inferred from CSI such as angle-of-arrival, time-of-flight, and Doppler frequency shift.