Map2APS: A Physically Grounded Benchmark for Direct Angle Power Spectrum Prediction from Urban Geometry

TL;DR

Map2APS introduces a large-scale, physically grounded benchmark for direct angle power spectrum prediction from urban geometry, enabling standardized evaluation of models in this domain.

Contribution

It provides a comprehensive dataset from ray-tracing simulations, benchmarks models, and introduces a strong baseline for APS prediction in urban environments.

Findings

MS-AReg achieves a cosine similarity of 0.948 on the test set.

MS-AReg has a peak location error of 1.20 degrees.

The benchmark and code are publicly available at the provided GitHub link.

Abstract

Angle power spectrum (APS) characterizes the directional distribution of received signal power and is directly relevant to beam management and MIMO processing. While environment-aware learning has been widely studied for radio maps and path loss, direct map-to-APS prediction still lacks a standardized large-scale benchmark. This paper presents Map2APS, a physically grounded benchmark constructed from intelligent ray-tracing (IRT) path-level propagation records. Map2APS covers 51 equal-height urban maps and approximately 2.55 million Tx--Rx samples, with a strict cross-map split for evaluating generalization to unseen urban layouts. We benchmark representative model families and introduce MS-AReg as a strong reference baseline. On the full held-out test set of 249{,}993 samples, MS-AReg achieves a cosine similarity of 0.948, a peak location error of 1.20$^\circ$, and an inference latency of 0.101 ms/sample. We further report dominant-direction metrics, including Top-1 dominant peak hit rate and dominant peak recall, to evaluate whether predicted spectra preserve decision-relevant arrival directions. The benchmark, code, and evaluation scripts are released at https://github.com/UNIC-Lab/aps-data.