Lopez-Tapia Santiago, de la Blanca Nicolas Perez
IEEE Trans Image Process. 2021;30:4747-4759. doi: 10.1109/TIP.2021.3074821. Epub 2021 May 5.
Single Image Super-Resolution (SISR) is one of the low-level computer vision problems that has received increased attention in the last few years. Current approaches are primarily based on harnessing the power of deep learning models and optimization techniques to reverse the degradation model. Owing to its hardness, isotropic blurring or Gaussians with small anisotropic deformations have been mainly considered. Here, we widen this scenario by including large non-Gaussian blurs that arise in real camera movements. Our approach leverages the degradation model and proposes a new formulation of the Convolutional Neural Network (CNN) cascade model, where each network sub-module is constrained to solve a specific degradation: deblurring or upsampling. A new densely connected CNN-architecture is proposed where the output of each sub-module is restricted using some external knowledge to focus it on its specific task. As far we know, this use of domain-knowledge to module-level is a novelty in SISR. To fit the finest model, a final sub-module takes care of the residual errors propagated by the previous sub-modules. We check our model with three state-of-the-art (SOTA) datasets in SISR and compare the results with the SOTA models. The results show that our model is the only one able to manage our wider set of deformations. Furthermore, our model overcomes all current SOTA methods for a standard set of deformations. In terms of computational load, our model also improves on the two closest competitors in terms of efficiency. Although the approach is non-blind and requires an estimation of the blur kernel, it shows robustness to blur kernel estimation errors, making it a good alternative to blind models.
单图像超分辨率（SISR）是近年来受到越来越多关注的低级计算机视觉问题之一。当前的方法主要基于利用深度学习模型和优化技术的力量来逆转退化模型。由于其难度，主要考虑了各向同性模糊或具有小各向异性变形的高斯模糊。在这里，我们通过纳入实际相机运动中出现的大的非高斯模糊来拓宽这种情况。我们的方法利用退化模型，提出了一种卷积神经网络（CNN）级联模型的新公式，其中每个网络子模块被约束来解决特定的退化问题：去模糊或上采样。提出了一种新的密集连接CNN架构，其中每个子模块的输出使用一些外部知识进行限制，使其专注于其特定任务。据我们所知，在SISR中这种将领域知识应用于模块级别的做法是新颖的。为了拟合最优模型，最后一个子模块处理由前几个子模块传播的残余误差。我们在SISR中的三个最先进（SOTA）数据集上检查我们的模型，并将结果与SOTA模型进行比较。结果表明，我们的模型是唯一能够处理我们更广泛的变形集的模型。此外，对于一组标准变形，我们的模型超越了所有当前的SOTA方法。在计算负载方面，我们的模型在效率上也优于两个最接近的竞争对手。尽管该方法是非盲的，需要估计模糊核，但它对模糊核估计误差具有鲁棒性，使其成为盲模型的一个很好的替代方案。
