MSGS: Multispectral 3D Gaussian Splatting

TL;DR

This paper introduces MSGS, a multispectral extension to 3D Gaussian Splatting, enhancing view synthesis by incorporating spectral information for improved realism and spectral consistency.

Contribution

It extends 3D Gaussian Splatting with spectral radiance using spherical harmonics, enabling wavelength-aware rendering and better handling of complex materials.

Findings

Outperforms RGB-only 3DGS in image quality and spectral fidelity.

Excels in scenes with translucent materials and anisotropic reflections.

Maintains real-time efficiency and compactness of the original 3DGS.

Abstract

We present a multispectral extension to 3D Gaussian Splatting (3DGS) for wavelength-aware view synthesis. Each Gaussian is augmented with spectral radiance, represented via per-band spherical harmonics, and optimized under a dual-loss supervision scheme combining RGB and multispectral signals. To improve rendering fidelity, we perform spectral-to-RGB conversion at the pixel level, allowing richer spectral cues to be retained during optimization. Our method is evaluated on both public and self-captured real-world datasets, demonstrating consistent improvements over the RGB-only 3DGS baseline in terms of image quality and spectral consistency. Notably, it excels in challenging scenes involving translucent materials and anisotropic reflections. The proposed approach maintains the compactness and real-time efficiency of 3DGS while laying the foundation for future integration with physically based shading models.