SpectralGaussians: Semantic, spectral 3D Gaussian splatting for multi-spectral scene representation, visualization and analysis
This work addresses multi-spectral scene representation, visualization, and analysis for applications like scene editing, though it appears incremental as an extension of 3D Gaussian Splatting.
The authors tackled multi-spectral scene representation by extending 3D Gaussian Splatting with semantic and spectral data, achieving superior performance over existing methods like XNeRF and SpectralNeRF in quantitative and qualitative evaluations.
We propose a novel cross-spectral rendering framework based on 3D Gaussian Splatting (3DGS) that generates realistic and semantically meaningful splats from registered multi-view spectrum and segmentation maps. This extension enhances the representation of scenes with multiple spectra, providing insights into the underlying materials and segmentation. We introduce an improved physically-based rendering approach for Gaussian splats, estimating reflectance and lights per spectra, thereby enhancing accuracy and realism. In a comprehensive quantitative and qualitative evaluation, we demonstrate the superior performance of our approach with respect to other recent learning-based spectral scene representation approaches (i.e., XNeRF and SpectralNeRF) as well as other non-spectral state-of-the-art learning-based approaches. Our work also demonstrates the potential of spectral scene understanding for precise scene editing techniques like style transfer, inpainting, and removal. Thereby, our contributions address challenges in multi-spectral scene representation, rendering, and editing, offering new possibilities for diverse applications.