Search papers, labs, and topics across Lattice.
This paper introduces a two-stage framework for Radio Environment Map (REM) estimation that replaces LiDAR data with learned elevation maps predicted from satellite RGB imagery. A CNN is trained to estimate elevation maps from satellite imagery, which are then used as input to existing REM estimation architectures. Results show a 7.8% improvement in RMSE compared to image-only baselines, demonstrating a lightweight and scalable alternative to LiDAR-based REM estimation.
Ditch the expensive LiDAR: learned elevation maps from satellite imagery can boost radio environment map accuracy by nearly 8%.
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data such as LiDAR-derived point clouds, which are costly to acquire, several gigabytes per km2 in size, and quickly outdated in dynamic environments.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.
