The paper introduces Physics-Unrolled Hybrid Neural Operator (PU‑HNO), a three‑stage cascade that transforms low‑fidelity ray‑tracing outputs and scene priors into high‑fidelity indoor radio maps by sequentially modeling reflection, diffraction, and scattering. It demonstrates that, under conditionally unbiased label noise, the model can learn stable propagation structures and surpass its own training labels. Experiments on varied floorplans show PU‑HNO outperforming image‑to‑image baselines, wireless learning models, and monolithic neural operators in both image quality and wireless deployment metrics.
arXiv:2610.19015v1 Announce Type: new Abstract: Real measurements are too limited to train an accurate indoor pathloss predictor that works across a wide range of buildings. Large-scale synthetic pre...
arXiv:2609.00615v1 Announce Type: cross Abstract: The evolution toward sixth-generation (6G) wireless networks is driving larger antenna arrays and highly directional multi-beam transmission, making...
arXiv:2607. 01777v1 Announce Type: cross Abstract: Radio frequency (RF) maps provide a compact representation of multipath propagation characteristics and are fundamental to channel modeling, coverage analysis, and environment-aware wireless optimization.
WiNeRF is a neural field framework that learns a spatially continuous, complex-valued wireless channel representation from sparse channel state information collected by commodity WiFi devices. It incorporates system constraints such as antenna geometry, limited spatial resolution, and phase uncertainty through a 3D conical wave sampling model, a multi-resolution implicit scene representation, and a differentiable optimization framework. In diverse indoor environments with non‑line‑of‑sight regions, WiNeRF achieves a median prediction SNR of 5.3 dB, outperforming prior neural baselines by 4.9 dB on average, and produces a task‑agnostic channel representation that can be reused in standard signal‑processing pipelines without hardware or protocol changes.
arXiv:2508. 03736v2 Announce Type: replace-cross Abstract: In this paper, we present a deep learning-based approach that integrates the DINOv2 architecture to improve building mapping by combining (possibly erroneous) maps from open-source platforms with pervasive radio frequency (RF) data collected from multiple wireless user equipments and base stations.
arXiv:2511. 05522v4 Announce Type: replace-cross Abstract: Accurate, low-latency channel modeling is essential for real-time wireless network simulation and digital-twin applications.
arXiv:2506.12045v2 Announce Type: replace-cross Abstract: Accurate reconstruction of latent environmental fields from sparse, indirect observations is a fundamental challenge across scientific domain...
arXiv:2405. 17366v3 Announce Type: replace Abstract: We present a novel machine-learning (ML) approach (EM-GANSim) for real-time electromagnetic (EM) propagation that is used for wireless communication simulation in 3D indoor environments.
The paper introduces PTNO, a neural operator that learns particle transport surrogates directly from noisy, low‑cost Monte Carlo (MC) labels, addressing high variance and high dynamic range challenges. By training on many noisy scenes, PTNO achieves comparable accuracy to converged MC while dramatically reducing computational cost, and it employs a softplus output and a pointwise relative L2 loss to handle HDR data. Experiments on neutron transport in fusion reactors and radiative transfer in participating media show speedups of up to 10⁵× and cost reductions of up to 10⁵× compared to traditional MC.
The paper introduces GCNO, a physics‑based, variable‑rate neural operator that compresses wireless channel matrices by identifying a sample‑dependent set of dominant propagation paths instead of treating the matrix as an image. GCNO leverages receive‑transmit channel structure, a first‑order Taylor correction, and least‑squares recovery to encode path directions and strengths, and the base station reconstructs the channel analytically from these tuples. Experiments on three ray‑traced environments show GCNO outperforms neural feedback baselines in reconstruction accuracy for the same payload or achieves the same accuracy with lower payload, and it generalizes to unseen antenna counts without retraining.
arXiv:2607. 16449v1 Announce Type: new Abstract: Accurate path loss prediction is a critical component of wireless network planning.
arXiv:2607. 28994v1 Announce Type: cross Abstract: High-fidelity radio fields are typically simulated for every scene--transmitter configuration or fitted separately to each scene, failing to exploit propagation structures shared across environments.