Differentiable Ray Tracing with Gaussians for Unified Radio Propagation Simulation and View Synthesis

TL;DR

This paper presents a novel framework that integrates neural scene representations with differentiable RF propagation simulation, enabling accurate electromagnetic path computation and high-quality view synthesis.

Contribution

It introduces a method embedding Gaussian primitives into ray tracing structures for unified RF simulation and visual rendering from neural reconstructions.

Findings

Neural reconstructions can serve as unified representations for RF propagation and view synthesis.

The framework enables point-to-point RF path computation within neural scenes.

Physically meaningful channel responses can be extracted from visual-only neural reconstructions.

Abstract

Explicit neural representations such as 3D Gaussian Splatting (3DGS) enable high-fidelity and real-time novel view synthesis, yet optimize for alpha-composited optical appearance rather than ray-intersectable geometry. In contrast, radio-frequency (RF) digital twins require deterministic multi-bounce paths, where the geometry dictates trajectories and their associated attenuation and delay. We introduce a framework enabling differentiable RF propagation simulation directly within visually reconstructed neural scenes, allowing point-to-point path computation between arbitrary 3D locations while preserving high-quality visual rendering. Unlike conventional RF simulation pipelines that rely on manually constructed meshes, we embed Gaussian primitives into a hardware-accelerated ray tracing structure as the underlying spatial representation. By extracting physically meaningful channel impulse responses from visual-only reconstructions, we provide cross-modal evidence that neural reconstructions can serve as unified spatial representations for both electromagnetic propagation simulation and photorealistic view synthesis.