Smooth Sparse Representation For Noise Robust Face Super-Resolution

Keywords

Fused Lasso; sparse representation; Super-resolution

Abstract

Face super-resolution has attracted much attention in recent years. Many algorithms have been proposed. Among them, sparse representation based face super-resolution approaches are able to achieve competitive performance. However, these sparse representation based approaches only perform well under the condition that the input is noiseless or has small noise. When the input is corrupted by large noise, the reconstruction weights of the input LR patches using sparse representation based approaches will be seriously unstable, thus leading to poor reconstruction results. To this end, in this paper, we propose a novel sparse representation based face super-resolution approach that incorporates a smooth prior to enforce similar training patches having similar sparse coding coefficients. Specifically, we introduce the fused Lasso to the least squares representation of the input LR image in order to obtain a stable sparse representation, especially when the noise level of the input LR image is high. Experiments are carried out on the benchmark FEI face dataset. Visual and quantitative comparisons show that the proposed face super-resolution method achieves comparable performance to the state-of-the-art methods under noiseless condition, and yields superior super-resolution results when the input LR face image is contaminated by strong noise.

Publication Date

1-4-2017

Publication Title

VCIP 2016 - 30th Anniversary of Visual Communication and Image Processing

Document Type

Article; Proceedings Paper

Personal Identifier

scopus

DOI Link

https://doi.org/10.1109/VCIP.2016.7805493

Socpus ID

85011115113 (Scopus)

Source API URL

https://api.elsevier.com/content/abstract/scopus_id/85011115113

This document is currently not available here.

Share

COinS