GSpaRC: Gaussian Splatting for Real-time Reconstruction of RF Channels

2025-11-27

AI Summary

To address the high spectral overhead (up to 25%) incurred by channel state information (CSI) acquisition in 5G wireless systems and the prohibitive inference latency (5–100 ms) of existing reconstruction methods—which hinder real-time deployment—this paper proposes a sub-millisecond RF channel reconstruction framework. We introduce 3D Gaussian splatting—a technique previously unexplored in RF modeling—combined with hemispherical equirectangular projection to emulate omnidirectional antenna responses, and integrate physics-informed priors with a lightweight neural network. A custom CUDA pipeline enables parallel computation across both frequency and spatial domains. Evaluated on multiple public RF datasets, our method achieves reconstruction accuracy competitive with state-of-the-art approaches, while accelerating training and inference by over 10× and achieving end-to-end latency under 1 ms. This significantly reduces pilot overhead and enables low-latency, real-time CSI acquisition for 5G and beyond-5G (B5G) systems.

Technology Category

• Cognitive Modeling & Cognitive Systems: Neural Spike Coding
• Machine Learning: Feature Construction/Reformulation
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Data management and stream processing for Web, mobile and wireless applications
• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation
• Search and Retrieval-Augmented AI: Personalized, context-aware and across-device search

Abstract

Channel state information (CSI) is essential for adaptive beamforming and maintaining robust links in wireless communication systems. However, acquiring CSI incurs significant overhead, consuming up to 25% of spectrum resources in 5G networks due to frequent pilot transmissions at sub-millisecond intervals. Recent approaches aim to reduce this burden by reconstructing CSI from spatiotemporal RF measurements, such as signal strength and direction-of-arrival. While effective in offline settings, these methods often suffer from inference latencies in the 5--100~ms range, making them impractical for real-time systems. We present GSpaRC: Gaussian Splatting for Real-time Reconstruction of RF Channels, the first algorithm to break the 1 ms latency barrier while maintaining high accuracy. GSpaRC represents the RF environment using a compact set of 3D Gaussian primitives, each parameterized by a lightweight neural model augmented with physics-informed features such as distance-based attenuation. Unlike traditional vision-based splatting pipelines, GSpaRC is tailored for RF reception: it employs an equirectangular projection onto a hemispherical surface centered at the receiver to reflect omnidirectional antenna behavior. A custom CUDA pipeline enables fully parallelized directional sorting, splatting, and rendering across frequency and spatial dimensions. Evaluated on multiple RF datasets, GSpaRC achieves similar CSI reconstruction fidelity to recent state-of-the-art methods while reducing training and inference time by over an order of magnitude. By trading modest GPU computation for a substantial reduction in pilot overhead, GSpaRC enables scalable, low-latency channel estimation suitable for deployment in 5G and future wireless systems. The code is available here: href{https://github.com/Nbhavyasai/GSpaRC-WirelessGaussianSplatting.git}{GSpaRC}.

Problem

• Reduces CSI acquisition overhead in wireless systems
• Enables real-time RF channel reconstruction under 1 ms
• Improves efficiency by using Gaussian splatting with physics-informed features

Innovation

• Uses 3D Gaussian primitives with lightweight neural models
• Employs equirectangular projection for omnidirectional RF reception
• Implements custom CUDA pipeline for parallelized sorting and rendering