Conference item icon

Conference item

Deep image prior

Abstract:

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 generator network is sufficient to capture a great deal of low-level image statistics prior to any learning. In order to do so, we show that a randomly-initialized neural network can be used as a handc...

Expand abstract
Publication status:
Published
Peer review status:
Peer reviewed
Version:
Accepted Manuscript

Actions


Access Document


Files:
Publisher copy:
10.1109/CVPR.2018.00984

Authors


Ulyanov, D More by this author
More by this author
Institution:
University of Oxford
Division:
MPLS Division
Department:
Engineering Science
Oxford college:
New College
Lempitsky, V More by this author
Publisher:
Institute for Electrical and Electronics Engineers Publisher's website
Publication date:
2018-12-17
Acceptance date:
2017-11-08
DOI:
Pubs id:
pubs:948554
URN:
uri:1f804ab6-b52b-4d8a-b4d8-41e5d7930834
UUID:
uuid:1f804ab6-b52b-4d8a-b4d8-41e5d7930834
Local pid:
pubs:948554

Terms of use


Metrics



If you are the owner of this record, you can report an update to it here: Report update to this record

TO TOP