Texture Synthesis from Samples(TSfS) is a new texture tiling technique developed in latest years, It can efficiently avoid.noticeable seams between texture patches and minimize the stretch and distortion of the pattern when tiling a texture on surfaces, and also can avoid the inconvenient work when using Procedural.Texture Synthesis method. It attracts more and more researcher’s attention and become a hot topic in the field of computer graphics,computer vision and image processing. The technique has great.potential in many applications, especially in image editing, high ratio data compression, fast data transferring on the internet, real-time rendering for large scale of scenes, realistic nd non-photorealisitic.rendering etc. in this project ,we had proposed several new algorithms to solve the problem exsited in the field of texture synthesis study: fast texture synthesis using multiple seeds as.constraints, multi-sample based texture mixing, constrained multi-sample based texture synthesis and texture transfer. With the help of these technologies, new texture samples can be easily obtained by interactive editing the exsiting texture samples and painting styles can be transferred automatically from source images to the target image. Especially the painting styles leaning technology also provides a new idea for the non-photorealisitic rendering.
研究纹理合成及其绘制的关键技术。研究内容包括基于参数控制的图象纹理合成和混合合成的方法,视频纹理的合成和混合合成的方法,三维曲面上图象纹理和几何纹理的合成方法,多种纹理图象的融合方法及其具有手绘风格的计算机绘画的生成方法。本项目的研究在计算机动画、虚拟现实等领域以及网络传输、数据压缩、影视特效等方面都有广泛的应用前景。
{{i.achievement_title}}
数据更新时间:2023-05-31
基于公众情感倾向的主题公园评价研究——以哈尔滨市伏尔加庄园为例
基于协同表示的图嵌入鉴别分析在人脸识别中的应用
一种改进的多目标正余弦优化算法
面向工件表面缺陷的无监督域适应方法
采用深度学习的铣刀磨损状态预测模型
基于反向纹理合成的视频编码技术研究
基于形象感知的多样图约束纹理合成技术研究
基于数据驱动的纹理元素分析、合成与编辑技术研究
基于纹理建模的预测编码技术研究