Meyer L, Grün J, Weiherer M, Egger B, Stamminger M, Franke L (2026)
Publication Type: Journal article
Publication year: 2026
DOI: 10.1111/cgf.70337
3D Gaussian Splatting (3DGS) [KKLD23] has transformed novel-view synthesis from RGB images, yet remains restricted to the visible spectrum. Many applications, including agricultural monitoring, rely on multi-spectral imaging, where spectral camera alignment and scalability pose major challenges. We present MS-Splatting—a multi-spectral 3DGS framework enabling unified multi-view consistent reconstruction and rendering across both visible and invisible spectra. Our key component is a neural color representation that encodes per-primitive features shared across spectral bands, decoded through a shallow multi-layer perceptron into spectrum-specific radiance. By leveraging inter-band correlations, this formulation enhances detail while reducing memory consumption compared to independent band modeling via per-channel modeling with spherical harmonics. Our method enables accurate parallax-free novel-view vegetation index rendering for plant monitoring and enhances RGB novel view synthesis quality by exploiting details revealed through multi-spectral bands. Our evaluation demonstrates that MS-Splatting exceeds the current leading methods in both categories. In addition, we introduce a multi-spectral dataset from aerial captures covering outdoor environments, specifically designed for evaluating these applications. We will release our code and dataset to facilitate further research. The project page is located at: https://meyerls.github.io/ms_splatting.
APA:
Meyer, L., Grün, J., Weiherer, M., Egger, B., Stamminger, M., & Franke, L. (2026). Multi-Spectral Gaussian Splatting with Neural Color Representation. Computer Graphics Forum. https://doi.org/10.1111/cgf.70337
MLA:
Meyer, Lukas, et al. "Multi-Spectral Gaussian Splatting with Neural Color Representation." Computer Graphics Forum (2026).
BibTeX: Download