arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1809.04789cs.CV
收藏

基于深度学习的兼顾定量和感知质量的图像超分辨率

Deep Learning-based Image Super-Resolution Considering Quantitative and Perceptual Quality

Yonsei University(延世大学)

Jun-Ho Choi, Jun-Hyuk Kim, Manri Cheon, Jong-Seok Lee

摘要:

最近,已经表明,在超分辨率中,在超分辨率图像的定量和感知质量之间存在折衷关系,其分别对应于与地面实况图像的相似性和自然度。在本文中,我们提出了一种新的超分辨率方法,可以提高感知质量的放大图像,同时保持传统的定量性能。所提出的方法采用深度网络进行多遍升级,同时使用一个神经网络和两个定量分数预测器网络。实验结果表明,该方法实现了定量和感知质量的良好平衡,表现出更令人满意的结果比现有的方法。

英文摘要:

Recently, it has been shown that in super-resolution, there exists a tradeoff relationship between the quantitative and perceptual quality of super-resolved images, which correspond to the similarity to the ground-truth images and the naturalness, respectively. In this paper, we propose a novel super-resolution method that can improve the perceptual quality of the upscaled images while preserving the conventional quantitative performance. The proposed method employs a deep network for multi-pass upscaling in company with a discriminator network and two quantitative score predictor networks. Experimental results demonstrate that the proposed method achieves a good balance of the quantitative and perceptual quality, showing more satisfactory results than existing methods.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑