arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1904.05802cs.CV
收藏

基于深度自适应双网络的难度感知图像超分辨率

Difficulty-aware Image Super Resolution via Deep Adaptive Dual-Network

Sun Yat-sen University(中山大学)

Jinghui Qin, Ziwei Xie, Yukai Shi, Wushao Wen

摘要:

近年来,基于深度学习的单图像超分辨率(SR)方法取得了很大的发展。现有的超分辨率方法通常采用前馈流水线来建立低分辨率(LR)和高分辨率(HR)图像之间的非线性映射。然而,由于平等地对待所有图像区域,而不考虑难度的多样性,这些方法满足一个上限的优化。为了解决这个问题,我们提出了一种新的SR方法,该方法根据图像中的每个图像区域的难度来区分处理图像中的每个图像区域。具体来说,我们提出了一个双向SR网络,其中一种方法被训练为专注于容易的图像区域,另一种方法被训练为处理硬图像区域。为了识别图像中的难易区域,提出了一种基于PSNR先验的图像难易识别网络。我们的SR方法,使用区域掩码自适应地执行双向SR网络产生优越的结果。在几个标准基准上进行了广泛的实验(例如,Set5,Set14,BSD 100和Urban100)表明,我们的方法实现了最先进的性能。

英文摘要:

Recently, deep learning based single image super-resolution(SR) approaches have achieved great development. The state-of-the-art SR methods usually adopt a feed-forward pipeline to establish a non-linear mapping between low-res(LR) and high-res(HR) images. However, due to treating all image regions equally without considering the difficulty diversity, these approaches meet an upper bound for optimization. To address this issue, we propose a novel SR approach that discriminately processes each image region within an image by its difficulty. Specifically, we propose a dual-way SR network that one way is trained to focus on easy image regions and another is trained to handle hard image regions. To identify whether a region is easy or hard, we propose a novel image difficulty recognition network based on PSNR prior. Our SR approach that uses the region mask to adaptively enforce the dual-way SR network yields superior results. Extensive experiments on several standard benchmarks (e.g., Set5, Set14, BSD100, and Urban100) show that our approach achieves state-of-the-art performance.

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。

↑