Machine Learning Methods for Reverse Engineering of Defective Structured Surfaces [electronic resource] /

Machine Learning Methods for Parametrization in Curve and Surface Approximation -- Classification of Geometric Primitives in Point Clouds -- Image Inpainting for High-resolution Textures Using CNN Texture Synthesis.

Pascal Laube presents machine learning approaches for three key problems of reverse engineering of defective structured surfaces: parametrization of curves and surfaces, geometric primitive classification and inpainting of high-resolution textures. The proposed methods aim to improve the reconstruction quality while further automating the process. The contributions demonstrate that machine learning can be a viable part of the CAD reverse engineering pipeline. Contents Machine Learning Methods for Parametrization in Curve and Surface Approximation Classification of Geometric Primitives in Point Clouds Image Inpainting for High-resolution Textures Using CNN Texture Synthesis Target Groups Lecturers and students in the field of machine learning, geometric modeling and information theory Practitioners in the field of machine learning, surface reconstruction and CAD The Author Pascal Laube’s main research interest is the development of machine learning methods for CAD reverse engineering. He is currently developing self-driving cars for an international operating German enterprise in the field of mobility, automotive and industrial technology.