Learned Elevation Models as a Lightweight Alternative to LiDAR for Radio Environment Map Estimation

2026-04-07

AI Summary

This study addresses the challenge of radio environment map (REM) estimation in high-frequency wireless communications, where conventional approaches rely on costly and non-scalable LiDAR-based 3D data. To overcome this limitation, the authors propose a two-stage framework that first predicts elevation maps from satellite RGB imagery and then estimates REMs using antenna parameters—entirely eliminating the need for 3D data during inference. This work presents the first method to replace LiDAR with only 2D remote sensing images for REM modeling, significantly enhancing practicality while preserving input feature consistency. Experimental results demonstrate that the proposed CNN architecture achieves up to a 7.8% reduction in RMSE compared to image-only baseline methods, effectively improving the accuracy of REM estimation.

Abstract

Next-generation wireless systems such as 6G operate at higher frequency bands, making signal propagation highly sensitive to environmental factors such as buildings and vege- tation. Accurate Radio Environment Map (REM) estimation is therefore increasingly important for effective network planning and operation. Existing methods, from ray-tracing simulators to deep learning generative models, achieve promising results but require detailed 3D environment data such as LiDAR-derived point clouds, which are costly to acquire, several gigabytes per km2 in size, and quickly outdated in dynamic environments. We propose a two-stage framework that eliminates the need for 3D data at inference time: in the first stage, a learned estimator predicts elevation maps directly from satellite RGB imagery, which are then fed alongside antenna parameters into the REM estimator in the second stage. Across existing CNN- based REM estimation architectures, the proposed approach improves RMSE by up to 7.8% over image-only baselines, while operating on the same input feature space and requiring no 3D data during inference, offering a practical alternative for scalable radio environment modelling.

Problem

• Radio Environment Map
• LiDAR
• 6G
• elevation estimation
• wireless propagation

Innovation

• Learned Elevation Models
• Radio Environment Map
• LiDAR-free inference
• Satellite RGB imagery
• 6G propagation modeling