期刊论文

Zhang, Baochang

英文

Pattern Recognition

0031-3203

2016

60

1

543-553

10.1016/j.patcog.2016.05.031

This work is partially supported by the National Natural Science Foundation of China (Grant nos. 61502153 , 61572064 , 61272052 , and 61473086 ), the National Basic Research Program of China ( 2015CB352501 ), the Program for New Century Excellent Talents in University of Ministry of Education of China, Beijing Municipal Science & Technology Commission ( Z161100001616005 ), the Natural Science Foundation of Hunan Province of China ( 2016JJ3031 ), the Construct Program of the Key Discipline in Hunan Province, the Doctorial Start-up Fund of Hengyang Normal University ( 15B22 ), the CICAEET fund , and the PAPD fund . The authors are thankful to Dr. Huixuan Tang for her help on proofreading. The authors thank all reviewers for their thorough and constructive suggestions.

本校为第一机构

3D reconstruction from a single 2D line drawing is an important but challenging problem in computer vision. Existed methods usually fail when line drawings contain large degree of noise named sketch errors. In this paper, we present an example-based approach to reconstructing 3D object, either planar or curved, from a single-view line drawing with sketch errors. Our method is to first decompose the input line drawing into primitive components and cluster them into local groups, then turn each group into 3D shapes via a novel example-based algor...