Deep learning of curvature features for shape completion Hernández Bautista, Marina Melero Rus, Francisco Javier Shape completion Curvature representation Parameterization Inpainting The paper presents a novel solution to the issue of incomplete regions in 3D meshes obtained through digitization. Traditional methods for estimating the surface of missing geometry and topology often yield unrealistic outcomes for intricate surfaces. To overcome this limitation, the paper proposes a neural network-based approach that generates points in areas where geometric information is lacking. The method employs 2D inpainting techniques on color images obtained from the original mesh parameterization and curvature values. The network used in this approach can reconstruct the curvature image, which then serves as a reference for generating a polygonal surface that closely resembles the predicted one. The paper’s experiments show that the proposed method effectively fills complex holes in 3D surfaces with a high degree of naturalness and detail. This paper improves the previous work in terms of a more in-depth explanation of the different stages of the approach as well as an extended results section with exhaustive experiments. 2023-10-13T07:52:48Z 2023-10-13T07:52:48Z 2023-07-16 journal article M. Hernández-Bautista and F.J. Melero. Deep learning of curvature features for shape completion. Computers & Graphics 115 (2023) 204–215[https://doi.org/10.1016/j.cag.2023.07.007] https://hdl.handle.net/10481/84960 10.1016/j.cag.2023.07.007 eng http://creativecommons.org/licenses/by-nc-nd/4.0/ open access Attribution-NonCommercial-NoDerivatives 4.0 Internacional Elsevier