RadioDiff-3D: A 3D$ imes$3D Radio Map Dataset and Generative Diffusion Based Benchmark for 6G Environment-Aware Communication

2025-07-16

AI Summary

Existing radio map construction methods rely predominantly on two-dimensional path-loss modeling, neglecting critical spatiotemporal channel characteristics—including angle-of-arrival (AoA), time-of-arrival (ToA), and vertical dimensionality—resulting in poor generalization. To address this, we introduce UrbanRadio3D, the first large-scale, high-resolution 3D×3D radio map dataset enabling joint three-dimensional spatial modeling of path loss, AoA, and ToA. We further propose RadioDiff-3D, a diffusion-based generative framework that synergistically integrates ray-tracing simulation with a 3D convolutional U-Net architecture to reconstruct high-fidelity 3D radio maps under both radiation-aware and radiation-agnostic scenarios. Extensive experiments on UrbanRadio3D demonstrate that RadioDiff-3D significantly outperforms state-of-the-art methods in accuracy, fidelity, and robustness. This work establishes a scalable, high-precision paradigm for 3D wireless channel modeling, directly advancing environment-aware communication for 6G systems.

Technology Category

• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Computer Vision: 3D Computer Vision
• Intelligent Robots: Localization, Mapping, and Navigation

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Location- and context-aware Web and WoT applications and services
• User Modeling, Personalization and Recommendation: User modeling and simulation for interactive and conversational systems
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

Abstract

Radio maps (RMs) serve as a critical foundation for enabling environment-aware wireless communication, as they provide the spatial distribution of wireless channel characteristics. Despite recent progress in RM construction using data-driven approaches, most existing methods focus solely on pathloss prediction in a fixed 2D plane, neglecting key parameters such as direction of arrival (DoA), time of arrival (ToA), and vertical spatial variations. Such a limitation is primarily due to the reliance on static learning paradigms, which hinder generalization beyond the training data distribution. To address these challenges, we propose UrbanRadio3D, a large-scale, high-resolution 3D RM dataset constructed via ray tracing in realistic urban environments. UrbanRadio3D is over 37$ imes$3 larger than previous datasets across a 3D space with 3 metrics as pathloss, DoA, and ToA, forming a novel 3D$ imes$33D dataset with 7$ imes$3 more height layers than prior state-of-the-art (SOTA) dataset. To benchmark 3D RM construction, a UNet with 3D convolutional operators is proposed. Moreover, we further introduce RadioDiff-3D, a diffusion-model-based generative framework utilizing the 3D convolutional architecture. RadioDiff-3D supports both radiation-aware scenarios with known transmitter locations and radiation-unaware settings based on sparse spatial observations. Extensive evaluations on UrbanRadio3D validate that RadioDiff-3D achieves superior performance in constructing rich, high-dimensional radio maps under diverse environmental dynamics. This work provides a foundational dataset and benchmark for future research in 3D environment-aware communication. The dataset is available at https://github.com/UNIC-Lab/UrbanRadio3D.

Problem

• Existing methods lack 3D spatial variations in radio maps
• Current approaches ignore key channel parameters like DoA and ToA
• Static learning paradigms limit generalization in radio map construction

Innovation

• Large-scale 3D radio map dataset via ray tracing
• UNet with 3D convolutional operators for benchmarking
• Diffusion-model-based generative framework for 3D maps