PropSplat: Map-Free RF Field Reconstruction via 3D Gaussian Propagation Splatting
2026-05-08 • Machine Learning
Machine Learning
AI summaryⓘ
The authors introduce PropSplat, a method to predict how radio signals spread without needing detailed maps or lots of measurements. Instead of traditional mapping, they use special 3D shapes called Gaussian primitives to model the signal loss directly from a few signal readings. They tested PropSplat on outdoor and indoor data, showing it predicts signal strength and location more accurately than other recent methods. This approach means fewer data and less geography knowledge are needed to model wireless signal environments.
radio frequency propagationGaussian primitivespath lossray tracingwireless localizationNeRFRMSEsub-6 GHzBluetooth Low Energysignal strength prediction
Authors
William Bjorndahl, Maninder Pal Singh, Farhad Nouri, Joseph Camp
Abstract
Building a site-specific propagation model typically requires either ray-tracing over detailed 3D maps or dense measurement campaigns. Both approaches are expensive and often infeasible for rapid deployments where geographic data is unavailable or outdated. We present PropSplat, a map-free propagation modeling method that reconstructs radio frequency (RF) fields using 3D anisotropic Gaussian primitives. Each Gaussian encodes a scalar path loss offset relative to an explicit baseline path loss model with a learnable path loss exponent. Gaussians are initialized along observed transmitter--receiver paths and optimized end-to-end to learn the propagation environment without external information like floor plans, terrain databases, or clutter data. We evaluate PropSplat against wireless radiance field methods NeRF$^2$, GSRF, and WRF-GS+ on two real-world datasets. On large-scale outdoor drive-tests spanning multiple topographical regions at six sub-6 GHz frequencies, PropSplat achieves 5.38 dB RMSE when training measurements are spaced 300m apart and outperforms WRF-GS+ (5.87 dB), GSRF (7.46 dB), and NeRF$^2$ (14.76 dB). On indoor Bluetooth Low Energy measurements, PropSplat achieves 0.19m mean localization error, an order of magnitude better than NeRF$^2$ (1.84m), while achieving near-identical received signal strength prediction accuracy. These results show that accurate site-specific propagation reconstruction is achievable from sparse RF-native measurements. The need for geographic data as a prerequisite for scalable RF environment modeling is reduced.