Gaussian Heritage: 3D Digitization of Cultural Heritage with Integrated Object Segmentation
This work addresses the slow, expensive, and expert-dependent methods in cultural heritage digitization, offering a more accessible solution for preservation and dissemination.
The paper tackles the problem of creating digital replicas of cultural heritage objects by proposing a pipeline that uses only RGB images from a smartphone to generate 3D models with integrated object segmentation, eliminating the need for manual annotation and making it affordable and easy to deploy.
The creation of digital replicas of physical objects has valuable applications for the preservation and dissemination of tangible cultural heritage. However, existing methods are often slow, expensive, and require expert knowledge. We propose a pipeline to generate a 3D replica of a scene using only RGB images (e.g. photos of a museum) and then extract a model for each item of interest (e.g. pieces in the exhibit). We do this by leveraging the advancements in novel view synthesis and Gaussian Splatting, modified to enable efficient 3D segmentation. This approach does not need manual annotation, and the visual inputs can be captured using a standard smartphone, making it both affordable and easy to deploy. We provide an overview of the method and baseline evaluation of the accuracy of object segmentation. The code is available at https://mahtaabdn.github.io/gaussian_heritage.github.io/.