Single image super-resolution (SISR), as a traditional ill-conditioned inverse problem, has been greatly revitalized by the recent development of convolutional neural networks (CNN). These CNN-based methods generally map a low-resolution image to its corresponding high-resolution version with sophisticated network structures and loss functions, showing impressive performances. This paper provides a new insight on conventional SISR algorithm, and proposes a substantially different approach relying on the iterative optimization. A novel iterative super-resolution network (ISRN) is proposed on top of the iterative optimization. We first analyze the observation model of image SR problem, inspiring a feasible solution by mimicking and fusing each iteration in a more general and efficient manner. Considering the drawbacks of batch normalization, we propose a feature normalization (F-Norm, FN) method to regulate the features in network. Furthermore, a novel block with FN is developed to improve the network representation, termed as FNB. Residual-in-residual structure is proposed to form a very deep network, which groups FNBs with a long skip connection for better information delivery and stabling the training phase. Extensive experimental results on testing benchmarks with bicubic (BI) degradation show our ISRN can not only recover more structural information, but also achieve competitive or better PSNR/SSIM results with much fewer parameters compared to other works. Besides BI, we simulate the real-world degradation with blur-downscale (BD) and downscale-noise (DN). ISRN and its extension ISRN+ both achieve better performance than others with BD and DN degradation models.
翻译:单一图像超级分辨率(SISR)是一个传统的不完善的反向问题,由于最近的进化神经网络(CNN)的发展而大大恢复了它。这些以CNN为基础的方法一般地将低分辨率图像映射为相应的高分辨率版本,带有复杂的网络结构和损失功能,表现令人印象深刻。本文对传统的SISSR算法提供了新的洞察力,并提出了以迭代优化为基础的完全不同的方法。在迭代优化之外还提出了一个新的迭代超级分辨率网络(ISRN)。我们首先分析图像SR问题的观测模型,以更笼统和高效的方式模拟和使用每一次迭代,从而鼓励一种可行的解决方案。考虑到分批正常化的缺陷,我们建议一种特性正常化(F-Norm,FN)方法来规范网络的特征。此外,与FNNR(I-RD)相比,一个全新的迭代超级迭代超级分辨率网络(I-RM)结构结构结构结构,建议形成一个非常深的网络,将FBNBs与一个较长的连接,以更好的信息交付和稳定性 Stal-SR结构阶段相比,我们也可以进行更深入的B-S-RBSBSBB-B-RB的实验性测试结果, 和B-RB-B-B-B-B-BB-S-S-B-B-S-S-B-S-S-S-S-S-S-S-S-S-S-S-S-S-S-BB-B-B-Bervial 只能进行更深入的实验性更深入的实验性更深入的升级的实验性测试。