Vision Transformers for Efficient Indoor Pathloss Radio Map Prediction

• DOI: 10.48550/arxiv.2412.09507
• Publication Date: 2024-12-12
• Authors: Edvard Ghukasyan; Hrant Khachatrian; Rafayel Mkrtchyan; Theofanis P. Raptis

Vision Transformers (ViTs) have demonstrated remarkable success in achieving state-of-the-art performance across various image-based tasks and beyond. In this study, we employ a ViT-based neural network to address the problem of indoor pathloss radio map prediction. The network's generalization ability is evaluated diverse settings, including unseen buildings, frequencies, antennas with varying radiation patterns. By leveraging extensive data augmentation techniques pretrained DINOv2 weights, achieve promising results, even under most challenging scenarios.