Face hallucination based on sparse local-pixel structure

作者：

Highlights：

• Our framework aims to shape the prior model using sparse representation.

• Global structure and local-pixel structure are incorporated to produce plausible facial details.

• A method to learn local-pixel structures based on sparse representation is proposed.

• The proposed method is competitive with other, state-of-the-art face-hallucination methods.

摘要

•Our framework aims to shape the prior model using sparse representation.•Global structure and local-pixel structure are incorporated to produce plausible facial details.•A method to learn local-pixel structures based on sparse representation is proposed.•The proposed method is competitive with other, state-of-the-art face-hallucination methods.

论文关键词：SR,super resolution,HR,high resolution,LR,low resolution,PSNR,peak signal to noise ratio,SSIM,Structural Similarity Index,SRM,sparse representation models,NARM,nonlocal autoregressive model,Face hallucination,Sparse local-pixel structure,Super-resolution,Sparse representation

论文评审过程：Received 21 January 2013, Revised 28 June 2013, Accepted 16 September 2013, Available online 24 September 2013.

论文官网地址：https://doi.org/10.1016/j.patcog.2013.09.012