Progressive perception-oriented network for single image super-resolution
Progressive perception-oriented network for single image super-resolution
复制标题
用于单图像超分辨率的渐进感知导向网络
DOI：
10.1016/j.ins.2020.08.114
复制
发表时间：
2021
影响因子：
8.1
通讯作者：
Wang Xiumei
中科院分区：
文献类型：
--
作者：
Hui Zheng;Li Jie;Gao Xinbo;Wang Xiumei
最近的研究表明，深度神经网络可以显著提高单幅图像的超分辨率性能。许多研究都集中在提高超分辨率(SR)图像的定量质量上。然而，这些以峰值信噪比最大化为目标的方法通常会在较大的放大因子下产生模糊图像。生成性对抗网络(GANS)的引入可以缓解这一问题，并在合成高频纹理方面显示出令人印象深刻的结果。然而，这些基于GaN的方法总是倾向于添加假纹理甚至伪影来制作视觉上更高分辨率的SR图像。在本文中，我们提出了一种新颖的感知图像超分辨率方法，该方法通过构建一个阶段性网络来逐步产生视觉上高质量的结果。具体地说，第一阶段致力于最小化像素级误差，第二阶段利用前一阶段提取的特征来追求具有更好结构保持性的结果。最后一阶段采用第二阶段提取的精细结构特征，以产生更逼真的结果。通过这种方式，我们可以尽可能地保持感知图像中的像素和结构层次信息。值得注意的是，所提出的方法可以在前馈过程中构建三种类型的图像。此外，我们还探索了一种采用多尺度分层特征融合的生成器。在基准数据集上的大量实验表明，我们的方法优于最先进的方法。代码可在https://github.com/Zheng222/PPON.上找到
Recently, it has been demonstrated that deep neural networks can significantly improve the performance of single image super-resolution (SISR). Numerous studies have concentrated on raising the quantitative quality of super-resolved (SR) images. However, these methods that target PSNR maximization usually produce blurred images at large upscaling factor. The introduction of generative adversarial networks (GANs) can mitigate this issue and show impressive results with synthetic high-frequency textures. Nevertheless, these GAN-based approaches always have a tendency to add fake textures and even artifacts to make the SR image of visually higher-resolution. In this paper, we propose a novel perceptual image super-resolution method that progressively generates visually high-quality results by constructing a stage-wise network. Specifically, the first phase concentrates on minimizing pixel-wise error, and the second stage utilizes the features extracted by the previous stage to pursue results with better structural retention. The final stage employs fine structure features distilled by the second phase to produce more realistic results. In this way, we can maintain the pixel, and structural level information in the perceptual image as much as possible. It is useful to note that the proposed method can build three types of images in a feed-forward process. Also, we explore a new generator that adopts multi-scale hierarchical features fusion. Extensive experiments on benchmark datasets show that our approach is superior to the state-of-the-art methods. Code is available at https://github.com/Zheng222/PPON.