首页 | 本学科首页   官方微博 | 高级检索  
     

基于格式塔的建筑物图画抽象
引用本文:南亮亮,Andrei Sharf,谢科,Tien-Tsin Wong,Oliver Deussen,Daniel Cohen-Or,陈宝权. 基于格式塔的建筑物图画抽象[J]. 计算机辅助设计与图形学学报, 2012, 24(2): 152-154
作者姓名:南亮亮  Andrei Sharf  谢科  Tien-Tsin Wong  Oliver Deussen  Daniel Cohen-Or  陈宝权
作者单位:1. 中国科学院深圳先进技术研究院可视计算中心 深圳518055
2. Department of Computer Science, Ben-Gurion University, Beer-Sheva, Israel
3. Department of Computer Science & Engineering, Chinese University of Hong Kong, Hong Kong
4. Department of Computer and Information Science, University of Konstanz, Konstanz, Germany
5. Department of Computer Science, Tel Aviv University, Tel Aviv, Israel
基金项目:国家自然科学基金,国家"八六三"高技术研究发展计划,中国科学院百人计划
摘    要:格式塔(Gestalt)理论总结了人类认知规则、模式和语义的若干规律,已有大量的研究针对独立的格式塔规则建立计算模型,但建立多个格式塔规则相互作用的耦合模型仍然是一个挑战.基于格式塔理论的若干主要规则建立了一个针对多个格式塔规则耦合的计算模型,并将该模型用于建筑物线画图的抽象;通过减少图画中重复结构元素的数目,或者将复杂的结构用简单结构替换的方式对建筑物结构进行概括和抽象.实验结果表明,该方法可以应用于风格各异的建筑物线画图,并可以扩展到其他类型的图画以及三维模型.

关 键 词:简化  抽象  格式塔

Conjoining Gestalt Rules for Abstraction of Architectural Drawings
Nan Liangliang , Andrei Sharf , Xie Ke , Tien-Tsin Wong , Oliver Deussen , Daniel Cohen-Or , Chen Baoquan. Conjoining Gestalt Rules for Abstraction of Architectural Drawings[J]. Journal of Computer-Aided Design & Computer Graphics, 2012, 24(2): 152-154
Authors:Nan Liangliang    Andrei Sharf    Xie Ke    Tien-Tsin Wong    Oliver Deussen    Daniel Cohen-Or    Chen Baoquan
Affiliation:1) 1)(Visual Computing Center,Shenzhen Institutes of Advanced Technology,Chinese Academy of Sciences,Shenzhen 518055) 2)(Department of Computer Science,Ben-Gurion University,Beer-Sheva,Israel) 3)(Department of Computer Science & Engineering,Chinese University of Hong Kong,Hong Kong) 4)(Department of Computer and In formation Science,University of Konstanz,Konstanz,Germany) 5)(Department of Computer Science,Tel Aviv University,Tel Aviv,Israel)
Abstract:We present a method for structural summarization and Abstraction of complex spatial arrangements found in architectural drawings.The method is based on the well-known Gestalt rules,which summarize how forms,patterns,and semantics are perceived by humans from bits and pieces of geometric information.Although defining a computational model for each rule alone has been extensively studied,modeling a conjoint of Gestalt rules remains a challenge.In this work,we develop a computational framework which models Gestalt rules and more importantly,their complex interactions.We apply conjoining rules to line drawings,to detect groups of objects and repetitions that conform to Gestalt principles.We summarize and Abstract such groups in ways that maintain structural semantics by displaying only a reduced number of repeated elements,or by replacing them with simpler shapes.We show an application of our method to line drawings of architectural models of various styles,and the potential of extending the technique to other computer-generated illustrations,and three-dimensional models.
Keywords:simplification  Abstraction  Gestalt
本文献已被 CNKI 万方数据 等数据库收录!
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号