Image-Based Approach for Preparing Artifacts for Virtual Puppetry Museum

In this paper, we present a method for creating a database of 3D puppet models to be used in a virtual puppetry museum. Our method involves extracting the shape, light, and material properties of a puppet from a sequence of input images. We generated 3D models from the data and evaluated them using PSNR, SSIM, and LPIPS metrics, which showed favorable results. We also had the 3D puppet models assessed by expert puppet craftsmen, who awarded them a score of 8 or higher out of 10. Using this approach, we were able to create over 30 3D puppet models to populate a virtual museum dedicated to Te Tieu puppetry, a traditional art form recognized at the national level.