Burst super-resolution (SR) provides a possibility of restoring rich details from low-quality images. However, since low-resolution (LR) images in practical applications have multiple complicated and unknown degradations, existing non-blind (e.g., bicubic) designed networks usually lead to a severe performance drop in recovering high-resolution (HR) images. Moreover, handling multiple misaligned noisy raw inputs is also challenging. In this paper, we address the problem of reconstructing HR images from raw burst sequences acquired from modern handheld devices. The central idea is a kernel-guided strategy which can solve the burst SR with two steps: kernel modeling and HR restoring. The former estimates burst kernels from raw inputs, while the latter predicts the super-resolved image based on the estimated kernels. Furthermore, we introduce a kernel-aware deformable alignment module which can effectively align the raw images with consideration of the blurry priors. Extensive experiments on synthetic and real-world datasets demonstrate that the proposed method can perform favorable state-of-the-art performance in the burst SR problem.

翻译：然而,由于实际应用中的低分辨率(LR)图像有多重复杂和未知的降解,现有非盲人(例如双立方)设计的网络通常导致高分辨率图像恢复的性能严重下降。此外,处理多重错乱的噪音原始输入也具有挑战性。在本文件中,我们处理从现代手持装置获得的原始爆破序列中重建人力资源图像的问题。核心思想是一种内核指导战略,可以用两个步骤(内核建模和HR恢复)解决爆破的SR。以前的估计是原投入的爆裂内核,而后者预测的是根据估计的内核进行超溶解的图像。此外,我们引入了一个内核分解调整模块,可以有效地将原始图像与对模糊的前期的考虑相匹配。关于合成和现实世界数据集的广泛实验表明,拟议的方法可以在防爆SR问题中产生有利的状态性能。