论文标题
带有空间上下文幻觉的盲图超分辨率
Blind Image Super-Resolution with Spatial Context Hallucination
论文作者
论文摘要
深度卷积神经网络（CNN）在高性能计算的惊人改进以来，在单像超分辨率（SISR）中起着至关重要的作用。但是，大多数超分辨率（SR）方法仅着眼于恢复双学的降解。从随机模糊和嘈杂的低分辨率（LR）图像中重建高分辨率（HR）图像仍然是一个具有挑战性的问题。在本文中，我们在不知道降解内核的情况下提出了一个新颖的空间上下文幻觉网络（SCHN），以实现盲目的超级分辨率。我们发现，当模糊内核未知时，由于误差的累积，单独的脱毛和超分辨率可能会限制性能。因此，我们在一个框架中将deNoising，deblurring和超分辨率整合在一起，以避免这种问题。我们在两个高质量数据集（Div2k和flickr2k）上训练模型。当输入图像被随机模糊和噪声损坏时，我们的方法比最新方法更好。
Deep convolution neural networks (CNNs) play a critical role in single image super-resolution (SISR) since the amazing improvement of high performance computing. However, most of the super-resolution (SR) methods only focus on recovering bicubic degradation. Reconstructing high-resolution (HR) images from randomly blurred and noisy low-resolution (LR) images is still a challenging problem. In this paper, we propose a novel Spatial Context Hallucination Network (SCHN) for blind super-resolution without knowing the degradation kernel. We find that when the blur kernel is unknown, separate deblurring and super-resolution could limit the performance because of the accumulation of error. Thus, we integrate denoising, deblurring and super-resolution within one framework to avoid such a problem. We train our model on two high quality datasets, DIV2K and Flickr2K. Our method performs better than state-of-the-art methods when input images are corrupted with random blur and noise.
