Recent researches have achieved great progress on single image super-resolution(SISR) due to the development of deep learning in the field of computer vision. In these method, the high resolution input image is down-scaled to low resolution space using a single filter, commonly max-pooling, before feature extraction. This means that the feature extraction is performed in biased filtered feature space. We demonstrate that this is sub-optimal and causes information loss. In this work, we proposed a state-of-the-art convolutional neural network method called Dense U-net with shuffle pooling. To achieve this, a modified U-net with dense blocks, called dense U-net, is proposed for SISR. Then, a new pooling strategy called shuffle pooling is designed, which is aimed to replace the dense U-Net for down-scale operation. By doing so, we effectively replace the handcrafted filter in the SISR pipeline with more lossy down-sampling filters specifically trained for each feature map, whilst also reducing the information loss of the overall SISR operation. In addition, a mix loss function, which combined with Mean Square Error(MSE), Structural Similarity Index(SSIM) and Mean Gradient Error (MGE), comes up to reduce the perception loss and high-level information loss. Our proposed method achieves superior accuracy over previous state-of-the-art on the three benchmark datasets: SET14, BSD300, ICDAR2003. Code is available online.
翻译:最近的研究在单一图像超分辨率(SISR)方面取得了巨大进展,这是因为在计算机视觉领域发展了深层学习。在这些方法中,高分辨率输入图像在特性提取之前使用单一过滤器,通常是最大共享,将高分辨率输入图像降为低分辨率空间。这意味着特征提取是在有偏差的过滤过滤功能空间进行的。我们证明这是次最佳的,并造成信息丢失。在这项工作中,我们建议了一种称为Dense U-net的先进动态神经网络方法,该方法与SimCD共享。为了实现这一目标,为SISSR提出了一个使用密集块的、称为稠密的U-net的修改U-net。然后,设计了一个称为shauffle集合的新的集合战略,目的是取代密集的U-Net,用于缩小规模操作。我们这样做,我们有效地取代了SISSR管道中的手制过滤器,为每个特性地图专门培训了更多的损失下游过滤器,同时减少了SIM-U-net整个SIM操作的信息损失。此外,还提出了一种混合损失功能,即与我们的Sqreal IM 高清晰度数据丢失率(SIM) 和高清晰的GIGRALIRS) 。