Large Factor Image Super-Resolution With Cascaded Convolutional Neural Networks
Lists
Only you see this
Abstract
Recently, convolutional neural networks (CNNs) have attracted considerable attention in single image super-resolution (SISR) and have enabled great performance improvements. However, most of the existing methods super-resolve input images to the desired size with an interpolation operation during the beginning stage, which brings about heavy aliasing artifacts and high computational costs. Especially for large upsampling factors (e.g., 8×), it remains a challenge to restore high-quality results for deeply degraded images. To tackle this problem, we propose a cascaded super-resolution convolutional neural network (CSRCNN), which takes a single low-resolution (LR) image as an input and reconstructs high-resolution (HR) images in a progressive way. At each cascaded level, to help converge and improve the accuracy, a novel U-net based block with backprojection is first introduced, which exploits the mutual relation between HR and LR feature spaces. A refined block following the U-net block is also used to reconstruct the realistic texture details. In addition, we naturally utilize the strategy of curriculum learning, organizing the learning process from easy (small factors) to hard (large factors). Comprehensive experiments on benchmark datasets demonstrate that the proposed network achieves superior results compared with those of other state-of-the-art methods, particularly with the 8× upsampling factor.
BibTeX
@article{zhang2021large,
author = {Dongyang Zhang and Jie Shao and Zhenwen Liang and Lianli Gao and Heng Tao Shen},
title = {{Large Factor Image Super-Resolution With Cascaded Convolutional Neural Networks}},
journal = {IEEE Trans. Multimedia},
year = {2021},
url = {https://openreview.net/forum?id=bHfhtzfy2B},
}Loading related content...