Special Issue: “Advanced Deep Learning for Image Super-Resolution”
• 大类 : 工程技术 - 3区
• 小类 : 工程：电子与电气 - 3区
The aim of image super-resolution (SR) is to recover low-resolution (LR) input image or video to a visually desirable high-resolution (HR) one. HR images have more pixel densities and excellent details than LR images.Imaging techniques have been rapidly developed in the last decades, and the resolution has reached a new level. Image SR has a significant impact on many applications, such as remote sensing, video surveillance, medical image and face recognition. SR has attracted huge interest and presently is one of the hot research topics in image processing and computer vision.
Previously the image SR methods were simple and fast. Image restoration is the process of taking a corrupted image and estimating the original image, which is known to be an ill-posed inverse problem. For the past couple of years, researchers attracted to learning-based image SR. They applied machine learning and deep learning techniques to reconstruct the LR image. Recently, deep neural networks have shown their superior performance in SR. Though, there are many deep learning and image SR problems remain intact, e.g. different types of corruption, new applications, new architectures, large-scale images, depth images.
Hence, the scope of this special issue is to provide a forum for researchers to focus on deep learning for image SR. To do this, we invite papers (including a survey paper) in modeling, algorithm, system, and application of deep learning-based SR and to establish the latest efforts of relevant researchers.
The list of possible topics includes, but not limited to:
- New deep learning models for SR
- Deep learning for SR for special types of images
- Deep learning for SR with different or unknown types of corruption
- Deep learning for depth image SR
- Deep learning for SR in remote sensing, video surveillance, face recognition and medical imaging
- Deep learning with the traditional SR approaches