logo资料库

A Closed Form Solution to Natural Image MattingPPT讲解.ppt

第1页 / 共30页
第2页 / 共30页
第3页 / 共30页
第4页 / 共30页
第5页 / 共30页
第6页 / 共30页
第7页 / 共30页
第8页 / 共30页
资料共30页,剩余部分请下载后查看
Anat Levin, Dani Lischinski and Yair Weiss School of CS&Eng The Hebrew University of Jerusalem, Israel
Matting and compositing +
The matting equations I i F   i i  1(  i ) B i = x + x
Why is matting hard?
Why is matting hard?
Why is matting hard?
Why is matting hard? I i F   i i  1(  i ) B i Matting is ill posed: 7 unknowns but 3 constraints per pixel对应于每一个像素有RGB三个通道,三个方程对应7个未 知量
0 ]1,0[ 1 0 1 Previous approaches The trimap interface: •Bayesian Matting (Chuang et al, CVPR01) •Poisson Matting (Sun et al SIGGRAPH 04) •Random Walk (Grady et al 05) Scribbles interface: •Wang&Cohen ICCV05
分享到:
收藏