Title :
Inpainting from multiple views
Author :
Kang, Sung Ha ; Chan, Tony F. ; Soatto, Stefano
Abstract :
Inpainting refers to the task of filling in missing or damaged regions of an image. In this paper we are interested in the inpainting problem where the missing regions are so large that local inpainting methods fail. As an alternative to the local principle, we make use of other images with related global information to enable a reasonable inpainting. Our method has roughly three phases: landmark matching, interpolation, and copying. The experimental results obtained are promising.
Keywords :
image matching; image reconstruction; image sequences; interpolation; copying; damaged regions filling; image reconstruction; inpainting; interpolation; landmark matching; missing regions filling; optical flow; Computer science; Data mining; Filling; Image motion analysis; Image reconstruction; Image restoration; Interpolation; Mathematics; Motion pictures; Shape;
Conference_Titel :
3D Data Processing Visualization and Transmission, 2002. Proceedings. First International Symposium on
Print_ISBN :
0-7695-1521-4
DOI :
10.1109/TDPVT.2002.1024127
