数据驱动的建筑物立面重建-山东大学.PDF

第27 卷 第 11 期 计算机辅助设计与图形学学报 Vol. 27 No.11 2015 年 11 月 Journal of Computer-Aided Design Computer Graphics Nov. 2015 数据驱动的建筑物立面重建 1) 1) 2) 1)* 韩福波 , 汪云海 , 南亮亮 , 陈宝权 1) ( 山东大学计算机科学与技术学院 济南 250101) 2) (King Abdullah University of Science and Technology, Jeddah 23955-69001 Saudi Arabia) (baoquan@sdu.edu.cn) 摘 要: 提出了一种数据驱动的从单幅照片恢复建筑物立面深度信息的方法, 基于窗户的对称特性, 构造了一个马 尔可夫随机场模型来对建筑物的立面图像进行分割; 将分割的图像组织成图结构, 每一个分割区域作为一个图节点, 图中的边链接相邻节点; 然后, 利用图匹配的方法为每一个区域从数据库训练中寻找最优的结构匹配, 并对匹配结 果进行优化, 得到了较好的重建结果. 关键词：墙面重建; 深度恢复; 马尔可夫随机场; 图模型 中图法分类号：TP391.41 Data-Driven Facade Reconstruction Han Fubo1), Wang Yunhai1), Nan Liangliang2), and Chen Baoquan1)* 1) (School of Computer Science and Technology, Shandong University, Ji ʹnan 250101) 2) (King Abdullah University of Science and Technology, Jeddah 23955-69001 Saudi Arabia) Abstract: We proposed a new data-driven method to infer depth information from a single facade image. A fa- cade is firstly segmented into several regions. By exploiting the symmetry characteristics of facade elements (i.e., windows), we segment the facade image using a Markov random field (MRF) formulation. We represent each facade by a graph, in which each graph node represents a segmented image region with consistent ap- pearance, and each graph edge encodes the spatial relationship between two distinct image regions. Then we generate a semantic label for each region by automatically matching the graph with our predefined templates in the database. Finally, we perform a global optimization process to produce the final facade model. Experiments demonstrate that our approach can generate favorable results. Key words: facade reconstruction; depth recovery; Markov random field; graphi