Taming Vision Priors for Data Efficient mmWave Channel Modeling

Accurately modeling millimeter-wave (mmWave) propagation is essential for real-time AR and autonomous systems. Differentiable ray tracing offers a physics-grounded solution but still facing deployment challenges due to its over-reliance on exhaustive channel measurements or brittle, hand-tuned scene models for material properties. We present VisRFTwin, a scalable and data-efficient digital-twin framework that integrates vision-derived material priors with differentiable ray tracing. Multi-view images from commodity cameras are processed by a frozen Vision-Language Model to extract dense semantic embeddings, which are translated into initial estimates of permittivity and conductivity for scene surfaces. These priors initialize a Sionna-based differentiable ray tracer, which rapidly calibrates material parameters via gradient descent with only a few dozen sparse channel soundings. Once calibrated, the association between vision features and material parameters is retained, enabling fast transfer to new scenarios without repeated calibration. Evaluations across three real-world scenarios, including office interiors, urban canyons, and dynamic public spaces show that VisRFTwin reduces channel measurement needs by up to 10$\times$ while achieving a 59% lower median delay spread error than pure data-driven deep learning methods.

Fast Monte Carlo Dropout and Error Correction for Radio Transmitter Classification

Monte Carlo dropout may effectively capture model uncertainty in deep learning, where a measure of uncertainty is obtained by using multiple instances of dropout at test time. However, Monte Carlo dropout is applied across the whole network and thus significantly increases the computational complexity, proportional to the number of instances. To reduce the computational complexity, at test time we enable dropout layers only near the output of the neural network and reuse the computation from prior layers while keeping, if any, other dropout layers disabled. Additionally, we leverage the side information about the ideal distributions for various input samples to do `error correction' on the predictions. We apply these techniques to the radio frequency (RF) transmitter classification problem and show that the proposed algorithm is able to provide better prediction uncertainty than the simple ensemble average algorithm and can be used to effectively identify transmitters that are not in the training data set while correctly classifying transmitters it has been trained on.