MSGS: Multispectral 3D Gaussian Splatting
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917409521139712 |
|---|---|
| author | Zheng, Iris Tang, Guojun Doronin, Alexander Teal, Paul Zhang, Fang-Lue |
| author_facet | Zheng, Iris Tang, Guojun Doronin, Alexander Teal, Paul Zhang, Fang-Lue |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_13340 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | MSGS: Multispectral 3D Gaussian Splatting Zheng, Iris Tang, Guojun Doronin, Alexander Teal, Paul Zhang, Fang-Lue Computer Vision and Pattern Recognition Graphics I.3.7; I.4.8; I.2.10 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. |
| title | MSGS: Multispectral 3D Gaussian Splatting |
| topic | Computer Vision and Pattern Recognition Graphics I.3.7; I.4.8; I.2.10 |
| url | https://arxiv.org/abs/2604.13340 |