Search papers, labs, and topics across Lattice.
This paper introduces RadioDiff-v2, a dual-branch one-dimensional diffusion transformer designed to accurately predict angular power spectra (APS) for beam selection and receiver localization in 6G networks, particularly under challenging non-line-of-sight (NLOS) conditions. By framing the task as a perception-distortion problem, the model effectively retains essential multipath structures while minimizing distortion, outperforming existing baselines across multiple metrics in zero-shot tests involving diverse environments. Key results include a 0.39 dB Wasserstein-1 distance and a significant reduction in localization error, demonstrating the model's robustness and practical applicability in real-world scenarios.
RadioDiff-v2 achieves unprecedented accuracy in angular power spectrum prediction, significantly enhancing beam selection and localization in complex 6G environments.
Angular radio maps describe the received-power distribution over the angle of arrival and underpin beam selection and receiver localization in sixth-generation (6G) networks. Predicting the angular power spectrum (APS) from geometry is difficult, because the mapping is ill-posed in non-line-of-sight (NLOS) conditions and must generalize to unseen environments. Distortion-minimizing regressors return the conditional mean, which over-smooths the spectrum and erases the multipath structure that downstream tasks need. We cast the task as a perception-distortion problem and propose RadioDiff-v2, a dual-branch one-dimensional diffusion transformer trained with flow matching. It couples periodic angular encoding, adaptive layer-normalization conditioning, a Fourier angular mixer, and joint velocity and clean-signal heads. A per-metric estimator portfolio reads every deployment quantity from this single model, so that samples carry the distribution, the clean-signal head supplies a regression-grade point estimate, Bayes-optimal rules select beams, and the conditional likelihood localizes the receiver. We prove that a concentrated conditional yields a straight probability-flow trajectory that one step integrates exactly, identifying deterministic transport as the correct inductive bias. On a zero-shot test of 99 environments and one million links, RadioDiff-v2 leads every baseline on every metric, with a 0.39 dB Wasserstein-1 distance, per-bin error below the regression baseline, a 2.43 dB eight-beam NLOS sweep loss, and a 20.6-pixel localization error with four base stations. Code is available at https://github.com/UNIC-Lab/RadioDiff-v2.
