Title

Context-Constrained Hallucination For Image Super-Resolution

Abstract

This paper proposes a context-constrained hallucination approach for image super-resolution. Through building a training set of high-resolution/low- resolution image segment pairs, the high-resolution pixel is hallucinated from its texturally similar segments which are retrieved from the training set by texture similarity. Given the discrete hallucinated examples, a continuous energy function is designed to enforce the fidelity of high-resolution image to low-resolution input and the constraints imposed by the hallucinated examples and the edge smoothness prior. The re-constructed high-resolution image is sharp with minimal artifacts both along the edges and in the textural regions. ©2010 IEEE.

Publication Date

8-31-2010

Publication Title

Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition

Number of Pages

231-238

Document Type

Article; Proceedings Paper

Personal Identifier

scopus

DOI Link

https://doi.org/10.1109/CVPR.2010.5540206

Socpus ID

77956006189 (Scopus)

Source API URL

https://api.elsevier.com/content/abstract/scopus_id/77956006189

This document is currently not available here.

Share

COinS