Learned Elevation Models as a Lightweight Alternative to LiDAR for Radio Environment Map Estimation
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866914451325714432 |
|---|---|
| author | Milosheski, Ljupcho Močnik, Fedja Mohorčič, Mihael Fortuna, Carolina |
| author_facet | Milosheski, Ljupcho Močnik, Fedja Mohorčič, Mihael Fortuna, Carolina |
| contents | 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data such as LiDAR-derived point clouds, which are costly to acquire, several gigabytes per km2 in size, and quickly outdated in dynamic environments.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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_05520 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Learned Elevation Models as a Lightweight Alternative to LiDAR for Radio Environment Map Estimation Milosheski, Ljupcho Močnik, Fedja Mohorčič, Mihael Fortuna, Carolina Signal Processing Artificial Intelligence I.2.0; J.2 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. |
| title | Learned Elevation Models as a Lightweight Alternative to LiDAR for Radio Environment Map Estimation |
| topic | Signal Processing Artificial Intelligence I.2.0; J.2 |
| url | https://arxiv.org/abs/2604.05520 |