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

2026-03-13

AI Summary

This work addresses the high cost and low efficiency of traditional radio frequency (RF) map acquisition and the limited controllability of existing generative models under unsupervised settings. The authors propose SAIL, a novel framework that, for the first time, learns disentangled latent representations from unlabeled RF maps without any positional or orientation labels. By integrating InfoGAN with Wasserstein GAN and gradient penalty, SAIL decomposes the latent space such that discrete variables correspond to physically interpretable spatial regions while continuous variables encode transmitter orientation. This enables controllable, direction-specific synthesis during inference. Evaluated on ray-tracing data, the method achieves an SSIM of 0.8576 and a PSNR of 23.33 dB, demonstrating high generation quality, physical consistency, and controllability.

Technology Category

• Intelligent Robots: Localization, Mapping, and Navigation
• Machine Learning: Deep Generative Models & Autoencoders
• Natural Language Processing: Generation

Application Category

• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Economics, Online Markets and Human Computation: Economic ramifications for generative AI infrastructure and applications

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.

Problem

• RF map synthesis
• unsupervised learning
• generative AI
• wireless networks
• spatial-angular representation

Innovation

• unsupervised generative modeling
• interpretable latent representation
• spatial-angular disentanglement
• RF map synthesis
• InfoGAN