Optimizing and learning for super-resolution

Conference item

In multiple-image super-resolution, a high resolution image is estimated from a number of lower-resolution images. This involves computing the parameters of a generative imaging model (such as geometric and photometric registration, and blur) and obtaining a MAP estimate by minimizing a cost function including an appropriate prior. We consider the quite general geometric registration situation modelled by a plane projective transformation, and make two novel contributions: (i) in previous approaches the MAP estimate has been obtained by first computing and fixing the registration, and then computing the super-resolution image with this registration. We demonstrate that superior estimates are obtained by optimizing over both the registration and image; (ii) the parameters of the edge preserving prior are learnt automatically from the data, rather than being set by trial and error. We show examples on a number of real sequences including multiple stills, digital video, and DVDs of movies.

Authors: Pickup, LC; Roberts, SJ; Zisserman, A

• Publication status: Published
• Peer review status: Peer reviewed
• Publisher: BMVA Press
• Host title: BMVC 2006 - Proceedings of the British Machine Vision Conference 2006
• Volume: 2
• Pages: 46.1-46.10
• Publication date: 2006-01-01
• Event title: 17th British Machine Vision Conference (BMVC 2006)
• Event location: Edinburgh, Scotland, UK
• Event start date: 2006-09-04
• Event end date: 2006-09-07
• ISBN: 1-901725-32-4
• Language: English