Deep image prior

Deep convolutional networks have become a popular tool for image generation and restoration. Generally, their excellent performance is imputed to their ability to learn realistic image priors from a large number of example images. In this paper, we show that, on the contrary, the structure of a gene...

Πλήρης περιγραφή

Λεπτομέρειες βιβλιογραφικής εγγραφής
Κύριοι συγγραφείς: Ulyanov, D, Vedaldi, A, Lempitsky, V
Μορφή: Journal article
Γλώσσα:English
Έκδοση: Springer 2020