# RFGAN: RF-Based Human Synthesis

arXiv: https://arxiv.org/abs/2112.03727 · HTML: https://mlsanity.com/paper/2112.03727/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 28 of its 67 references that are in the map.
- First posted on arXiv 7 Dec 2021.

## Builds on (most cited first, 28 of 28)

- [A Style-Based Generator Architecture for Generative Adversarial Networks](https://mlsanity.com/paper/1812.04948/) (2018)
- [Image-to-Image Translation with Conditional Adversarial Networks](https://mlsanity.com/paper/1611.07004/) (2016)
- [Improved Techniques for Training GANs](https://mlsanity.com/paper/1606.03498/) (2016)
- [Conditional Generative Adversarial Nets](https://mlsanity.com/paper/1411.1784/) (2014)
- [Arbitrary Style Transfer in Real-time with Adaptive Instance Normalization](https://mlsanity.com/paper/1703.06868/) (2017)
- [Semantic Image Synthesis with Spatially-Adaptive Normalization](https://mlsanity.com/paper/1903.07291/) (2019)
- [Least Squares Generative Adversarial Networks](https://mlsanity.com/paper/1611.04076/) (2016)
- [Generative Adversarial Text to Image Synthesis](https://mlsanity.com/paper/1605.05396/) (2016)
- [Encoding in Style: a StyleGAN Encoder for Image-to-Image Translation](https://mlsanity.com/paper/2008.00951/) (2020)
- [Which Training Methods for GANs do actually Converge?](https://mlsanity.com/paper/1801.04406/) (2018)
- [StackGAN: Text to Photo-realistic Image Synthesis with Stacked Generative Adversarial Networks](https://mlsanity.com/paper/1612.03242/) (2016)
- [RMPE: Regional Multi-person Pose Estimation](https://mlsanity.com/paper/1612.00137/) (2016)
- [Beyond Short Snippets: Deep Networks for Video Classification](https://mlsanity.com/paper/1503.08909/) (2015)
- [GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium](https://mlsanity.com/paper/1706.08500/) (2017)
- [ManiGAN: Text-Guided Image Manipulation](https://mlsanity.com/paper/1912.06203/) (2019)
- [An Attention Enhanced Graph Convolutional LSTM Network for Skeleton-Based Action Recognition](https://mlsanity.com/paper/1902.09130/) (2019)
- [An End-to-End Spatio-Temporal Attention Model for Human Action Recognition from Skeleton Data](https://mlsanity.com/paper/1611.06067/) (2016)
- [RVOS: End-to-End Recurrent Network for Video Object Segmentation](https://mlsanity.com/paper/1903.05612/) (2019)
- [mm-Pose: Real-Time Human Skeletal Posture Estimation using mmWave Radars and CNNs](https://mlsanity.com/paper/1911.09592/) (2019)
- [Person-in-WiFi: Fine-grained Person Perception using WiFi](https://mlsanity.com/paper/1904.00276/) (2019)
- [Skeleton-Based Action Recognition with Spatial Reasoning and Temporal Stack Learning](https://mlsanity.com/paper/1805.02335/) (2018)
- [SPA-GAN: Spatial Attention GAN for Image-to-Image Translation](https://mlsanity.com/paper/1908.06616/) (2019)
- [Cycle In Cycle Generative Adversarial Networks for Keypoint-Guided Image Generation](https://mlsanity.com/paper/1908.00999/) (2019)
- [Learning Longterm Representations for Person Re-Identification Using Radio Signals](https://mlsanity.com/paper/2004.01091/) (2020)
- [Towards Domain-Independent and Real-Time Gesture Recognition Using mmWave Signal](https://mlsanity.com/paper/2111.06195/) (2021)
- [Quality-aware Unpaired Image-to-Image Translation](https://mlsanity.com/paper/1903.06399/) (2019)
- [Unsupervised Domain Adaptation for RF-based Gesture Recognition](https://mlsanity.com/paper/2111.10602/) (2021)
- [Deep Multi-Kernel Convolutional LSTM Networks and an Attention-Based Mechanism for Videos](https://mlsanity.com/paper/1908.08990/) (2019)

## Built on by (most cited first, 4 of 4)

- [Through-Wall Imaging based on WiFi Channel State Information](https://mlsanity.com/paper/2401.17417/) (2024)
- [RFPose-OT: RF-Based 3D Human Pose Estimation via Optimal Transport Theory](https://mlsanity.com/paper/2301.13013/) (2022)
- [High-resolution efficient image generation from WiFi CSI using a pretrained latent diffusion model](https://mlsanity.com/paper/2506.10605/) (2025)
- [WiCompass: Oracle-driven Data Scaling for mmWave Human Pose Estimation](https://mlsanity.com/paper/2602.18726/) (2026)

## Abstract (arXiv)

This paper demonstrates human synthesis based on the Radio Frequency (RF) signals, which leverages the fact that RF signals can record human movements with the signal reflections off the human body. Different from existing RF sensing works that can only perceive humans roughly, this paper aims to generate fine-grained optical human images by introducing a novel cross-modal RFGAN model. Specifically, we first build a radio system equipped with horizontal and vertical antenna arrays to transceive RF signals. Since the reflected RF signals are processed as obscure signal projection heatmaps on the horizontal and vertical planes, we design a RF-Extractor with RNN in RFGAN for RF heatmap encoding and combining to obtain the human activity information. Then we inject the information extracted by the RF-Extractor and RNN as the condition into GAN using the proposed RF-based adaptive normalizations. Finally, we train the whole model in an end-to-end manner. To evaluate our proposed model, we create two cross-modal datasets (RF-Walk & RF-Activity) that contain thousands of optical human activity frames and corresponding RF signals. Experimental results show that the RFGAN can generate target human activity frames using RF signals. To the best of our knowledge, this is the first work to generate optical images based on RF signals.