3D Scene Rendering with Multimodal Gaussian Splatting

TL;DR

This paper introduces a multimodal 3D scene rendering method combining RF sensing with Gaussian Splatting to improve robustness and efficiency, especially in challenging visual conditions.

Contribution

It presents a novel framework integrating RF signals with Gaussian Splatting, enabling high-quality 3D rendering with sparse RF data, addressing limitations of vision-only approaches.

Findings

RF integration improves robustness in adverse conditions

Efficient depth prediction from sparse RF data

High-fidelity 3D scene rendering achieved

Abstract

3D scene reconstruction and rendering are core tasks in computer vision, with applications spanning industrial monitoring, robotics, and autonomous driving. Recent advances in 3D Gaussian Splatting (GS) and its variants have achieved impressive rendering fidelity while maintaining high computational and memory efficiency. However, conventional vision-based GS pipelines typically rely on a sufficient number of camera views to initialize the Gaussian primitives and train their parameters, typically incurring additional processing cost during initialization while falling short in conditions where visual cues are unreliable, such as adverse weather, low illumination, or partial occlusions. To cope with these challenges, and motivated by the robustness of radio-frequency (RF) signals to weather, lighting, and occlusions, we introduce a multimodal framework that integrates RF sensing, such as automotive radar, with GS-based rendering as a more efficient and robust alternative to vision-only GS rendering. The proposed approach enables efficient depth prediction from only sparse RF-based depth measurements, yielding a high-quality 3D point cloud for initializing Gaussian functions across diverse GS architectures. Numerical tests demonstrate the merits of judiciously incorporating RF sensing into GS pipelines, achieving high-fidelity 3D scene rendering driven by RF-informed structural accuracy.