山脉图像轮廓线引导的三维虚拟地形合成  被引量:2

Terrain Synthesis Guided by Outlines of Mountain Image

在线阅读下载全文

作  者:李伟[1] 赵瑞斌[1] 庞明勇[1] Li Wei;Zhao Ruibin;Pang Mingyong(Department of Educational Technology, Nanjing Normal University, Nanjing 210097)

机构地区:[1]南京师范大学教育技术系,南京210097

出  处:《计算机辅助设计与图形学学报》2017年第12期2235-2244,共10页Journal of Computer-Aided Design & Computer Graphics

基  金:国家自然科学基金(41631175);江苏省社会科学基金(15TQB005);江苏高校优势学科建设工程项目

摘  要:三维地形在构建各种虚拟室外场景中具有重要的作用,而现有地形合成算法存在合成结果不可预期、合成过程人工参与较多等不足.为此,提出一种直观便捷且自动化的真实感三维地形合成算法.首先从用户给定的一幅二维图像中提取真实地形山脉轮廓线;然后借助卷积神经网络模型预测每一条轮廓线的深度,并根据深度和二维图像成像逆过程将轮廓线映射到三维空间;最后以三维空间中的轮廓线为地形的全局特征草图,以具有局部细节特征的地形块为基本元素,通过块拼接、融合、高程匹配等操作合成三维地形.实验结果表明,该算法能够在真实地形山脉轮廓线的约束下自动化地合成结果可预期的真实感三维地形.The3D terrain plays an important role in constructing various virtual outdoor scenes,but it is difficult for the existing terrain synthesis algorithms to automatically create realistic and predictable terrains.In this paper,we present a novel algorithm for conveniently and intuitively synthesizing3D digital terrains.The algorithm first extracts a set of mountain outlines from a given image,and evaluates the depths of the outlines with the deep convolutional neural network model and creates a depth image.The outlines are then mapped to3D space via the inverse process of planar imaging of3D objects.Subsequently,based on the mapped outlines in3D space,our method constructs a feature sketch to define global features of the terrain to be created.Taking a group of terrain blocks with local features,sampled from real terrains,as basic constructing elements,our method finally synthesizes the terrain by matching and blending the blocks guided by the feature sketch.Experiment results showed that,our algorithm can automatically synthesize realistic3D terrains with various features,which meet user’s expectations well under the constraint of real mountain outlines.

关 键 词:三维地形合成 山脉轮廓线 特征草图 深度图 

分 类 号:TP391.41[自动化与计算机技术—计算机应用技术]

 

参考文献:

正在载入数据...

 

二级参考文献:

正在载入数据...

 

耦合文献:

正在载入数据...

 

引证文献:

正在载入数据...

 

二级引证文献:

正在载入数据...

 

同被引文献:

正在载入数据...

 

相关期刊文献:

正在载入数据...

相关的主题
相关的作者对象
相关的机构对象