Zobrazeno 1 - 6
of 6
pro vyhledávání: '"Matveev, Albert"'
We present a pipeline for parametric wireframe extraction from densely sampled point clouds. Our approach processes a scalar distance field that represents proximity to the nearest sharp feature curve. In intermediate stages, it detects corners, cons
Externí odkaz:
http://arxiv.org/abs/2107.06165
Autor:
Matveev, Albert, Rakhimov, Ruslan, Artemov, Alexey, Bobrovskikh, Gleb, Egiazarian, Vage, Bogomolov, Emil, Panozzo, Daniele, Zorin, Denis, Burnaev, Evgeny
We propose Deep Estimators of Features (DEFs), a learning-based framework for predicting sharp geometric features in sampled 3D shapes. Differently from existing data-driven methods, which reduce this problem to feature classification, we propose to
Externí odkaz:
http://arxiv.org/abs/2011.15081
Estimation of differential geometric quantities in discrete 3D data representations is one of the crucial steps in the geometry processing pipeline. Specifically, estimating normals and sharp feature lines from raw point cloud helps improve meshing q
Externí odkaz:
http://arxiv.org/abs/2007.02571
Publikováno v:
Proc. of AIST, 2019
Reconstruction of directional fields is a need in many geometry processing tasks, such as image tracing, extraction of 3D geometric features, and finding principal surface directions. A common approach to the construction of directional fields from d
Externí odkaz:
http://arxiv.org/abs/1907.00559
Autor:
Koch, Sebastian, Matveev, Albert, Jiang, Zhongshi, Williams, Francis, Artemov, Alexey, Burnaev, Evgeny, Alexa, Marc, Zorin, Denis, Panozzo, Daniele
We introduce ABC-Dataset, a collection of one million Computer-Aided Design (CAD) models for research of geometric deep learning methods and applications. Each model is a collection of explicitly parametrized curves and surfaces, providing ground tru
Externí odkaz:
http://arxiv.org/abs/1812.06216
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.