摘要
在纹理合成过程中利用向量场作为指导,生成反映向量场大小和方向变化的合成结果·采用块纹理合成的流程,在对向量场合成块均匀划分的基础上,通过进一步的自适应分割,将向量场划分成为不同大小和不同形状的最终合成块,使之与向量场的变化趋势相吻合·对向量变化过于剧烈的区域,则采用点合成的方式进行纹理合成,以保证合成效果的平滑·实验表明,文中的方法可以实现快速而高质量的向量场可视化·
This paper presents a vector field visualization approach based on texture synthesis. The approach primarily adopts patch-based texture synthesis flow, synthesizing progressively-variant textures to reflect the diversification trend of vector fields. In the approach, the basic synthesis patches are divided adaptively into multi-layer, multiform sub-patches to fit the variety of vector field. In some patches where the inside vector data vary acutely, the pixel-based texture synthesis is adopted to preserve the smoothness of the synthesis results. Experimental results show that our method can generate appropriate textures to clearly exhibit the diversifications trend of module and direction in vector fields, achieving fast and high-qualified vector field visualization.
出处
《计算机辅助设计与图形学学报》
EI
CSCD
北大核心
2006年第11期1677-1682,共6页
Journal of Computer-Aided Design & Computer Graphics
基金
国家重点基础研究发展规划项目(2002CB312102)
国家自然科学基金(60473105)
澳门大学科研基金
关键词
纹理合成
科学计算可视化
向量场可视化
自适应分割
texture synthesis
visualization in scientific computing
vector field visualization
self-adaptive division