Bayesian image super-resolution, continued

Conference item

This paper develops a multi-frame image super-resolution approach from a Bayesian view-point by marginalizing over the unknown registration parameters relating the set of input low-resolution views. In Tipping and Bishop’s Bayesian image super-resolution approach [16], the marginalization was over the super- resolution image, necessitating the use of an unfavorable image prior. By inte- grating over the registration parameters rather than the high-resolution image, our method allows for more realistic prior distributions, and also reduces the dimen- sion of the integral considerably, removing the main computational bottleneck of the other algorithm. In addition to the motion model used by Tipping and Bishop, illumination components are introduced into the generative model, allowing us to handle changes in lighting as well as motion. We show results on real and synthetic datasets to illustrate the efficacy of this approach.

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

• Publication status: Published
• Peer review status: Peer reviewed
• Publisher: Curran Associates
• Host title: Advances in Neural Information Processing Systems 19): 20th Annual Conference on Neural Information Processing Systems 2006
• Volume: 2
• Pages: 1071-1079
• Series number: 19
• Publication date: 2007-12-01
• Event title: Twentieth Annual Conference on Neural Information Processing Systems
• Event location: Vancouver, B.C., Canada
• Event website: https://neurips.cc/Conferences/2006
• Event start date: 2006-12-04
• Event end date: 2006-12-07
• ISSN: 1049-5258
• ISBN: 9781622760381
• Language: English