000218020 001__ 218020
000218020 005__ 20190416220329.0
000218020 037__ $$aSTUDENT
000218020 245__ $$aGraph-based Image Inpainting
000218020 269__ $$a2014
000218020 260__ $$c2014
000218020 336__ $$aStudent Projects
000218020 520__ $$aThe project goal was to explore the applications of spectral graph theory to address the inpainting problem of large missing chunks. We used a non-local patch graph representation of the image and proposed a structure detector which leverages the graph representation and influences the fill-order of our exemplar-based algorithm. Our method achieved state-of-the-art performances.
000218020 6531_ $$ainpainting
000218020 6531_ $$agraph
000218020 700__ $$0249515$$g226056$$aDefferrard, Michaël
000218020 720_2 $$aVandergheynst, Pierre$$edir.$$g120906$$0240428
000218020 720_2 $$aPerraudin, Nathanaël$$edir.$$g179669$$0247306
000218020 720_2 $$aParatte, Johann$$edir.$$g174659$$0247305
000218020 720_2 $$aSchoenenberger, Yann Mikaël$$edir.$$g186768$$0248489
000218020 8564_ $$uhttps://github.com/mdeff/giin$$zURL
000218020 8564_ $$uhttps://infoscience.epfl.ch/record/218020/files/report.pdf$$zn/a$$s997746$$yn/a
000218020 909C0 $$xU10380$$0252392$$pLTS2
000218020 909CO $$qGLOBAL_SET$$pSTI$$ooai:infoscience.tind.io:218020
000218020 917Z8 $$x226056
000218020 917Z8 $$x226056
000218020 917Z8 $$x226056
000218020 937__ $$aEPFL-STUDENT-218020
000218020 973__ $$aEPFL
000218020 980__ $$bOTHER$$aSTUDENT