SAIL: Unsupervised Spatial-Angular Interpretable Feature Learning for RF Map Synthesis

TL;DR

SAIL is a novel GAN-based framework that learns interpretable, controllable features from unlabeled RF maps, enabling efficient and targeted synthesis for wireless network planning without supervision.

Contribution

SAIL introduces an unsupervised, interpretable, and controllable RF map synthesis method using a structured GAN that captures spatial and angular features without labeled data.

Findings

Achieves high-quality RF map synthesis with SSIM of 0.8576

Learns meaningful spatial-angular factors without supervision

Enables fast, targeted RF map generation for network planning

Abstract

In wireless networks, radio-frequency (RF) maps are critical for tasks such as capacity planning, coverage estimation, and localization. Traditional approaches for obtaining RF maps, including site surveys and ray-tracing simulations, are labor-intensive or computationally expensive, especially at high frequencies and dense network deployments. Generative AI offers a promising alternative for RF map synthesis. However, supervised methods are often infeasible due to the lack of reliable labeled training data, while purely unsupervised methods typically lack explicit control over the synthesis process. To address these challenges, we propose SAIL (Spatial-Angular Interpretable Feature Learning), a generative adversarial network (GAN)-based framework that learns interpretable and controllable latent variables directly from unlabeled RF maps and enables targeted RF map synthesis at inference time through latent-variable manipulation. SAIL builds on the information-maximizing GAN (InfoGAN) principle to learn a structured representation comprising: (i) a categorical latent variable that captures discrete floor-plan regions associated with Tx location and (ii) a continuous latent variable that captures angular variations corresponding to the Tx boresight angle, without requiring any location or orientation supervision during training. We further adopt a Wasserstein GAN objective with a gradient penalty to improve training stability and synthesis quality. Our results using ray-tracing-based RF maps indicate that SAIL learns physically meaningful spatial-angular factors and enables fast controlled RF map synthesis, achieving an average SSIM of 0.8576 and an average PSNR of 23.33 dB relative to ray-tracing simulations.