计算机科学与探索 ›› 2017, Vol. 11 ›› Issue (9): 1484-1495.DOI: 10.3778/j.issn.1673-9418.1608030

• 人工智能与模式识别 • 上一篇    下一篇

元素分布构建的三维模型表面纹理合成方法

桂  彦1,2,刘  杨1,2+,李  峰1,2   

  1. 1. 长沙理工大学 计算机与通信工程学院,长沙 410114
    2. 长沙理工大学 综合交通运输大数据智能处理湖南省重点实验室,长沙 410114
  • 出版日期:2017-09-01 发布日期:2017-09-06

3D Surfaces Texture Synthesis Based on Elements Distribution Construction

GUI Yan1,2, LIU Yang1,2+, LI Feng1,2   

  1. 1. School of Computer & Communication Engineering, Changsha University of Science & Technology, Changsha 410114, China
    2. Hunan Provincial Key Laboratory of Intelligent Processing of Big Data on Transportation, Changsha University of Science & Technology, Changsha 410114, China
  • Online:2017-09-01 Published:2017-09-06

摘要: 针对由纹理元素组成的样本纹理在模型表面纹理合成中难以保持样本纹理结构规律性的问题,提出了一种基于纹理元素分布构建的模型表面纹理合成方法。首先通过用户交互在三维模型表面上确定待合成纹理的初始位置,然后利用邻域比较以局部扩张-冲突检测的形式,从三维模型表面初始位置上开始逐步构建纹理元素的分布,使之与二维样本纹理的纹理元素分布具有一定的外观相似性。最后,采用自适应的局部参数化方法将纹理元素分别映射到模型表面对应位置,以获得最终的三维模型表面纹理合成结果。实验结果表明,该方法能够在模型表面合成高质量的纹理,并在保持纹理元素完整性和保持样本纹理潜在规律性的同时,能够使得已合成纹理中扭曲程度较低且是连续、无接缝的。

关键词: 模型表面纹理合成, 纹理元素分布, 邻域比较, 局部扩张

Abstract: This paper proposes a novel method for surfaces texture synthesis based on elements distribution construction, in order to preserve the underlying regularity of texture samples in the synthesized texture over surfaces. This paper firstly specifies an initial position on the 3D surface by user interaction, and then expands it outward by using local growth based on neighborhood comparisons under collision detection, in order to construct the distribution of texture elements over 3D surfaces, which maintains a certain visual resemblance with the input 2D reference connectivity. According to the positions information provided by the constructed distribution of texture elements, this paper obtains the final synthesized result by pasting the extracted texture elements onto the 3D surfaces. The    experimental results show that the proposed method can produce high quality textures over surfaces, which not only preserve the texture elements integrity and the underlying structural regularity well, but also guarantee low distortions and no cracks in the synthesized results.

Key words: surface texture synthesis, texture element distribution, neighborhood comparisons, local growth