Since non-blind Super Resolution (SR) fails to super-resolve Low-Resolution (LR) images degraded by arbitrary degradations, SR with the degradation model is required. However, this paper reveals that non-blind SR that is trained simply with various blur kernels exhibits comparable performance as those with the degradation model for blind SR. This result motivates us to revisit high-performance non-blind SR and extend it to blind SR with blur kernels. This paper proposes two SR networks by integrating kernel estimation and SR branches in an iterative end-to-end manner. In the first model, which is called the Kernel Conditioned Back-Projection Network (KCBPN), the low-dimensional kernel representations are estimated for conditioning the SR branch. In our second model, the Kernelized BackProjection Network (KBPN), a raw kernel is estimated and directly employed for modeling the image degradation. The estimated kernel is employed not only for back-propagating its residual but also for forward-propagating the residual to iterative stages. This forward-propagation encourages these stages to learn a variety of different features in different stages by focusing on pixels with large residuals in each stage. Experimental results validate the effectiveness of our proposed networks for kernel estimation and SR. We will release the code for this work.
翻译:由于无盲超级分辨率(SR)未能通过任意降解而使低分辨率(LR)图像退化,因此需要采用降解模型,但本文件显示,仅以各种模糊内核进行训练的无盲SR,其性能与盲人SR的降解模型相似。这促使我们重新审视高性能非盲性超分辨率(SR),并将之扩展至含模糊内核的盲性SR。本文提议通过将内核估计和SR分支以迭接式端至端的方式整合成两个SR网络。在第一个模型中,即Kernel Condiced 后投影网络(KCBPN),对低度内核表示进行了各种模糊内核内核显示与盲性模型相似的性能。在我们第二个模型中,内核反光后投影网络(KBPN),一个原始内核内核内核网被估计并直接用于模拟图像退化。估计的内核不仅用于对内核的残余部分进行后再分析,而且用于前方对后端阶段进行前方对后端分析。这个前方内核显示阶段的模拟模型将鼓励这些前方核反应网络的每个阶段学习不同的阶段。