Jul 2025· IEEE Journal of Selected Topics in Electromagnetics, Antennas and Propagation· Vol 2, pp. 386-400· 2 citations· 58 references
Computer Science
TL;DR
Photon Splatting is presented, a physics-guided neural surrogate for wireless channel modeling in complex quasi-static environments that generalizes to unseen Tx locations, Rx positions, and antenna beam patterns without retraining.
Abstract
We present Photon Splatting, a physics-guided neural surrogate for wireless channel modeling in complex quasi-static environments. The work represents wave-environment interactions using surface-attached virtual sources, or photons, which carry directional wave signatures informed by the scene geometry and transmitter (Tx) configuration. At runtime, channel impulse responses (CIRs) are predicted by splatting photon contributions onto the angular domain of the receiver (Rx) using a geodesic rasterizer and aggregating them in delay. The model is trained to learn a physically grounded representation that maps Tx–Rx configurations to full channel responses. After a one-time offline training phase, the surrogate generalizes to unseen Tx locations, Rx positions, and antenna beam patterns without retraining. We demonstrate the framework on Sionna ray-tracing data for canonical 3-D scenes and a complex indoor café with 1000 Rxs. The results show millisecond-level inference latency and accurate CIR predictions across a range of configurations.
Wireless signal reconstruction is essential for RF-based positioning in GPS-denied environments. However, multipath propagation, shadowing, and non-Gaussian noise complicate this, and traditional methods require extensive site-specific calibration that precludes rapid deployment. We present In-Context Signal Completion (ICSC), demonstrating that small language models fine-tuned with Group Relative Policy Optimization and physics-informed rewards can reconstruct RSSI across sequential extrapolation and spatial interpolation tasks. Our 0.5B-parameter model attains 55% recall within 2 dB and a 2.85 dB mean absolute error on sequential prediction. This achieves a 49% error reduction over the untrained baseline, performing on par with GPT-4o (51%) with fewer parameters. Successful zero-shot transfer to spatial interpolation indicates the model acquires transferable physical reasoning rather than task-specific memorization. Operating at 3 ms latency for real-time edge inference, ICSC reduces deployment from weeks of per-site data collection to immediate inference using sequential context.
High-frequency communication systems heavily rely on line-of-sight(LoS) paths, so blockage of the LoS path can cause severe performance loss. Near-field Airy beams with curved trajectories can steer energy around obstacles, offering a promising solution for blockage mitigation. However, existing methods for selecting a near-optimal Airy beam trajectory either rely on high-overhead beam training, or employ data-driven learning without a clear, physically interpretable rule. To address this problem, we propose a physics-guided neural Airy beamforming framework that selects a near-optimal trajectory in one shot with clear physical interpretability. Specifically, we first formulate a single-edge representation of the blocker model in 3GPP TR 38.901 and reveal the trajectory--edge coupling mechanism. This analysis yields a trajectory-selection optimality condition that defines the candidate trajectories. Although these trajectories generally cannot be expressed in closed form, we show that they form a continuous structure. This continuous structure is then exploited to construct a compact physics-defined region that captures near-optimal trajectories. Guided by this region, a lightweight neural predictor is finally designed to directly select a near-optimal trajectory without beam training. Simulations show that the compact physics-defined region effectively captures near-optimal trajectories, while occupying only about 6% of the candidate-space area on average. The proposed framework retains 99.7% of the reference rate obtained through numerical optimization, and nearly matches the rate of the data-driven method despite using approximately 112\times fewer neural-network parameters.
This paper develops a physics-informed neural network (PINN) framework for the lossy telegrapher equations and presents a coupled IEEE 738 thermal balance formulation intended as a structural blueprint for environmentally aware transmission-line digital twins. The baseline electromagnetic PINN maps (x,t)↦(V^,I^) and is empirically validated against a finite-difference time-domain (FDTD) reference solver. An augmented parametric framework Nθ:(x,t,e)↦(V^,I^,T^line) is mathematically derived, wherein the ambient vector e modulates a temperature-dependent resistance R′(Tline) and couples to the telegrapher residuals via a non-linear thermal balance residual rT. Two further constraints, a sag-tension consistency residual rS and a dynamic line rating (DLR) one-sided penalty rDLR, are formulated for completeness but are explicitly designated as architectural extension hooks running at zero weight (ωth=ωsag=ωdlr=0) within the reported microscale numerical benchmarks. Consequently, the empirical validation presented herein strictly concerns the baseline electromagnetic telegrapher PINN. The numerical results demonstrate robust L2 field convergence against FDTD reference data, highly structured error accumulation along physical characteristic curves, and reliable recovery of strongly observable parameters (L′,C′) from sparse, noisy terminal measurements. Conversely, the recovery of loss parameters (R′,G′) exhibits a severe structural weak identifiability that precisely matches the analytical predictions of a comprehensive Fisher Information Matrix analysis. The core contributions of this work are primarily methodological: (i) a dimensionally consistent, corrected residual formulation for the lossy telegrapher equations; (ii) an explicit positioning of the proposed multi-physics framework within the parametric PINN literature; (iii) a Fisher information identifiability diagnostic illustrating the near-degeneracy of baseline parameter estimation; and (iv) a clean algorithmic separation of forward training, inverse parameter identification, and prospective online updates.
Beamforming plays a key role in multiple-input-multiple-output (MIMO) communication systems. However, conventional beamforming design normally requires accurate instantaneous channel state information (CSI) and iterative optimization, which incur substantial pilot overhead and computational complexity. Recognizing that radio propagation is intrinsically governed by the physical geometry, we develop a 3D Gaussian splatting for environment-aware beamforming (GSBF) pipeline based on multi-modal data, which characterizes the environment through a persistent 3D Gaussian representation. Specifically, GSBF models the environmental scattering response with reciprocity-preserving bidirectional spherical Gaussian (Bi-SG) kernels and performs two-sided electromagnetic rasterization to render an angular propagator map. The rendered map is then aggregated through an over-complete array-manifold dictionary and projected to the constant-modulus beamformers, thereby synthesizing beams directly from the access point (AP) pose and user position without online instantaneous CSI. Simulations demonstrate that GSBF consistently outperforms baselines such as exhaustive beam alignment (EBA) with lower latency.
Yijie Bian, Wei Guo, Zixin Wang et al.· 0 citations
Non-line-of-sight (NLOS) imaging reconstructs hidden targets by characterizing indirect light propagation across visible relay surfaces. However, transient imaging typically relies on expensive hardware that is difficult to calibrate and operate. Transient light transport simulation thus serves as an effective alternative, supporting algorithm development, prototyping, and validation before implementing a physical experimental system. This paper introduces a physics-based simulation framework that incorporates bidirectional reflectance distribution function (BRDF) weighting for relay and target surfaces, geometric attenuation, and contact probabilistic sampling. To capture realistic time-delayed photon behavior and system blurring, the framework further integrates a gamma-distribution-based multipath tail model and an optional Gaussian-blurred instrument response function (IRF) module. Simulation and ablation studies validate that the proposed framework can produce high-fidelity and stable transient volume data. In particular, BRDF and multipath tail modeling substantially make the simulated data more consistent with real weak-echo propagation behavior, while the parameterized pipeline achieves a practical trade-off between reconstruction fidelity and computational efficiency.
ZengYiFan Chen, Chunhui Wang, Yanmin Sun et al.· International Conference on...· 0 citations
Recent advances in 3D Gaussian Splatting (3DGS)-based wireless radiance field (WRF) reconstruction provide an efficient solution for wireless channel modeling. However, existing WRF reconstruction methods rely on pre-collected observations and offline optimization, and thus struggle to provide real-time channel knowledge. To bridge this gap, we propose CORF-GS, a real-time WRF reconstruction framework that processes sequential optical and radio frequency (RF) keyframes. Specifically, CORF-GS constructs a unified Gaussian representation for optical and RF with shared geometry and modality-specific appearance, allowing high-resolution optical images to provide structural priors for WRF reconstruction. When a new keyframe arrives, CORF-GS first employs optical-guided Gaussian sampling to densify the WRF in under-represented regions. Since light and radio waves may respond differently to the same object surfaces due to wavelength mismatch, relying solely on optical guidance may neglect RF-informative areas. Therefore, CORF-GS performs coupled optical-RF optimization to jointly refine the shared Gaussians. Compared with the existing two-stage training pipelines, this prevents WRF from passively adapting to a frozen optical geometry and encourages the shared Gaussians to adapt to both optical structures and RF power distributions. Simulations show that CORF-GS achieves state-of-the-art RF spectrum synthesis quality and reduces the reconstruction time by $6.4\times$ compared with existing WRF methods.
