一种保留几何及属性边界的网格简化方法

Simplification of unclosed mesh models with geometry and property boundary preservation

在实际应用领域,三维模型除包含由三角形网格构成的几何、拓扑信息外,还包含颜色、纹理、法矢量等属性信息,因此数据量较大,且不可避免地存在边界和孔洞.基于三角形折叠的方法,对误差矩阵的计算和误差控制方法进行了改进,并提出了几何及属性边界三角形的概念,给出了一种保留原始模型边界及属性信息的简化算法.该算法针对不同的边界情况将原始三角形网格划分为边界三角形、角点三角形、内部三角形及特征三角形,并采取相应的约束策略,在减小模型数据量的同时,较好地保留了边界和属性信息,并且生成递进网格文件,为包含属性的非封闭网格模型提供了连续多分辨率的模型重现.实验结果证明该方法快速有效,已成功应用于基于W eb的三维递进传输和发布.

In practice, property information such as colors, textures, surface normals, etc. is necessary to represent 3 D models besides geometry and topology information of triangle meshes, which will inevitably result in a large volume of 3 D data as well as boundary edges and holes of mesh models. In order to decrease the data volume as well as preserve significant character of 3D models, an improved quadric error metrics and error control method were used to present a new simplification algorithm of unclosed mesh models based on trianstrategies were adopted to preserve appearance and boundary of the original models during the simplification process. In addition, a method to generate progressive meshes was given to provide a continuous multi-resolution representation of 3D models. The proposed method has been successfully applied to progressive transmission and presentation system of 3D models over the Internet.