4.4 Article

Cascaded face super-resolution with shape and identity priors

期刊

IET IMAGE PROCESSING
卷 17, 期 11, 页码 3309-3322

出版社

WILEY
DOI: 10.1049/ipr2.12863

关键词

image enhancement; image reconstruction; image resolution

向作者/读者索取更多资源

In this study, the cascaded super-resolution network (CSRNet) is proposed to address the challenge of reconstructing high-resolution faces from low-resolution inputs. CSRNet utilizes a cascaded structure and incorporates shape and identity priors to improve the authenticity of the generated super-resolution faces. The proposed method outperforms existing state-of-the-art methods in terms of quantitative and qualitative evaluations.
Despite impressive progress in face super-resolution (SR), it is an open challenge to reconstruct a reliable SR face that preserves authentic facial characteristics. Here, the problem of super-resolving low-resolution (LR) faces to high-resolution (HR) ones is addressed. To tackle the ill-posed nature of face SR, the cascaded super-resolution network (CSRNet) is proposed to utilize shape and identity priors jointly and progressively, the first to explore multiple priors. Specifically, CSRNet adopts a cascaded structure to transform an LR face to HR face progressively via multiple stages. At each stage, CSRNet forces its output face image to match both the shape priors and identity priors extracted from the ground-truth HR face. The shape priors estimated in one stage are merged into the inputs of its subsequent stage to provide rich information for the face SR. To generate realistic yet discriminative faces, the cascaded super-resolution generative adversarial network (CSRGAN) is also proposed to incorporate the adversarial loss and identification loss into CSRNet. Extensive experiments on popular benchmarks show that the CSRNet and CSRGAN outperform existing face SR state-of-the-art methods, both quantitatively and qualitatively, and detailed ablation studies show the advantage of this method.

作者

我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。

评论

主要评分

4.4
评分不足

次要评分

新颖性
-
重要性
-
科学严谨性
-
评价这篇论文

推荐

暂无数据
暂无数据