ECCV2014:labelindex

Yan Wang, Sunghyun Cho, Jue Wang, Shih-Fu Chang. Discriminative Indexing for Probabilistic Image Patch Priors. In European Conference on Computer Vision (ECCV), September 2014.

Download [help]

Download paper: Adobe portable document (pdf)

Copyright notice:This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. These works may not be reposted without the explicit permission of the copyright holder.

Abstract

Newly emerged probabilistic image patch priors, such as Expected Patch Log-Likelihood (EPLL), have shown excellent performance on image restoration tasks, especially deconvolution, due to its rich expressiveness. However, its applicability is limited by the heavy computation involved in the associated optimization process. Inspired by the recent advances on using regression trees to index priors defined on a Conditional Random Field, we propose a novel discriminative indexing approach on patch-based priors to expedite the optimization process. Specifically, we propose an efficient tree indexing structure for EPLL, and overcome its training tractability challenges in high-dimensional spaces by utilizing special structures of the prior. Experimental results show that our approach accelerates state-of-the-art EPLL-based deconvolution methods by up to 40 times, with very little quality compromise

Contact

Yan Wang
Yong Wang
Jun Wang
Shih-Fu Chang

BibTex Reference

@InProceedings{ECCV2014:labelindex,
   Author = {Wang, Yan and Cho, Sunghyun and Wang, Jue and Chang, Shih-Fu},
   Title = {Discriminative Indexing for Probabilistic Image Patch Priors},
   BookTitle = {European Conference on Computer Vision (ECCV)},
   Month = {September},
   Year = {2014}
}

EndNote Reference [help]

Get EndNote Reference (.ref)

For problems or questions regarding this web site contact The Web Master.