arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1904.07523cs.CV
收藏

超分辨率研究综述

A Deep Journey into Super-resolution: A survey

Data61, CSIRO(澳大利亚联邦科学与工业研究组织Data61);IIAI;ANU(澳大利亚国立大学)

Saeed Anwar, Salman Khan, Nick Barnes

摘要:

基于深度卷积网络的超分辨率是一个快速发展的领域,具有许多实际应用。在本次博览会中,我们广泛比较了30多个最先进的超分辨率卷积神经网络(CNN)在三个经典和三个最近推出的具有挑战性的数据集上,以基准测试单个图像的超分辨率。我们引入了一种基于深度学习的超分辨率网络分类法,将现有方法分为九类,包括线性、残差、多分支、递归、渐进、基于注意力和对抗性设计。我们还在网络复杂性、内存占用、模型输入和输出、学习细节、网络损失类型和重要的架构差异(例如,深度、跳过连接、过滤器)。进行的广泛评估显示,在过去几年中,准确性持续快速增长,同时模型复杂性和大规模数据集的可用性也相应提高。人们还注意到,被确定为基准的开创性方法已被目前的竞争者大大超越。尽管近年来取得了进展,我们确定了现有技术的几个缺点,并提供未来的研究方向对这些开放的问题的解决方案。

英文摘要:

Deep convolutional networks based super-resolution is a fast-growing field with numerous practical applications. In this exposition, we extensively compare 30+ state-of-the-art super-resolution Convolutional Neural Networks (CNNs) over three classical and three recently introduced challenging datasets to benchmark single image super-resolution. We introduce a taxonomy for deep-learning based super-resolution networks that groups existing methods into nine categories including linear, residual, multi-branch, recursive, progressive, attention-based and adversarial designs. We also provide comparisons between the models in terms of network complexity, memory footprint, model input and output, learning details, the type of network losses and important architectural differences (e.g., depth, skip-connections, filters). The extensive evaluation performed, shows the consistent and rapid growth in the accuracy in the past few years along with a corresponding boost in model complexity and the availability of large-scale datasets. It is also observed that the pioneering methods identified as the benchmark have been significantly outperformed by the current contenders. Despite the progress in recent years, we identify several shortcomings of existing techniques and provide future research directions towards the solution of these open problems.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑