Zhao, ChenxiFan, ChuanmaoMohadikar, PayalDuan, YeChaine, RaphaëlleDeng, ZhigangKim, Min H.2023-10-092023-10-092023978-3-03868-234-9https://doi.org/10.2312/pg.20231287https://diglib.eg.org:443/handle/10.2312/pg202312873D reconstruction plays a significant role in various fields, including medical imaging, architecture, and forensic science, in both research and industry. The quality of color is one of the criteria that determine reconstruction performance. However, the predicted color from deep learning often suffers from low quality and a lack of details. While traditional texture mapping methods can provide superior color, they are restricted by mesh quality. In this study, we propose Color3D, a comprehensive procedure that applies photorealistic colors to the reconstructed mesh, accommodating both static objects and animations. The necessary inputs include multiview RGB images, depth images, camera poses, and camera intrinsic. Compared to traditional methods, our approach replaces face colors directly from the texture map with vertex colors from multiview images. The colors of the faces are obtained by interpolating the vertex colors of each triangle. Our method can generate high-quality color for different objects, and the performance remains strong even when the input mesh is not perfect.Attribution 4.0 International LicenseCCS Concepts: Computing methodologies -> Texturing; Image processing; Computer graphics; Mesh modelsComputing methodologiesTexturingImage processingComputer graphicsMesh models10.2312/pg.20231287123-1242 pages