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.

Spectral rendering accurately simulates light-material interactions by considering the entire light spectrum, unlike traditional rendering methods that use limited color channels like RGB. This technique is particularly valuable in industries to assess visual quality before production. Moreover, Spectral imaging finds extensive applications in fields like agriculture for plant disease detection, cultural heritage for preservation, forensic science, environment monitoring and medical science among others. Advances in generating novel views from images have been achieved through methods like NERF and Gaussian splatting, which outperforms others in terms of quality. This paper introduces a web-based viewer built on the Viser framework for visualizing and comparing cross-spectral Gaussian splats from different views and during various training stages. This viewer supports real-time collaboration and comprehensive visual comparison, enhancing user experience in spectral data analysis. We conduct a user study and performance analysis to confirm its effectiveness and usability for different application scenarios, while also proposing potential enhancements for increased functionality.

Accurately replicating the appearance of real-world materials in computer graphics is a complex task due to the intricate interactions between light, reflectance, and geometry. In this paper we address the challenges of material representation, acquisition, and editing by leveraging the potential of deep learning algorithms our framework provide. To enable the visualization and generation of material assets from single or multi-view images, allowing for the estimation of materials from real world objects. Additionally, a material asset exporter, enabling the export of materials in widely used formats and facilitating easy editing using common content creator tools. The proposed framework enables designers to effectively collaborate and seamlessly integrate deep learning-based material estimation models into their design pipelines using traditional content creation tools. An analysis of the performance and memory usage of material assets at various texture resolutions shows that our framework can be used plausibly according to the needs of the end-user.