»ã±¨±êÌâ (Title)£ºExemplar-based Image Colorization: From Variational Model to Deep Architecture£¨»ùÓÚÑùÀýµÄͼÏñ×ÅÉ«£º´Ó±ä·ÖÄ£Ð͵½Éî¶È½á¹¹£©

»ã±¨ÈË (Speaker)£º ·½·¢ÏÖ ½ÌÊÚ£¨»ª¶«Ê¦·¶´óѧ£©

»ã±¨¹¦·ò (Time)£º2023Äê11ÔÂ1ÈÕ(ÖÜÈý ) 13:30

»ã±¨µØÖ· (Place)£ºÐ£±¾²¿ F420

Ô¼ÇëÈË(Inviter)£ºÎÂÖÇæ¼

Ö÷°ì²¿ÃÅ£ºÀíѧԺÊýѧϵ

»ã±¨ÌáÒª£º Exemplar-based image colorization refers to a computer-assisted process that adds colors to grayscale images. It is a challenging task since there is usually no one-to-one correspondence between color and local texture. Existing methods either perform poorly on some datasets or have strict requirements on reference images (content, position), which limits their practical application. In this talk, we will address such issue from the perspectives of variational method and deep learning architecture. Extensive experiments will also be displayed to demonstrate their superiority.