论文标题
SRZOO：使用深度学习的集成存储库
SRZoo: An integrated repository for super-resolution using deep learning
论文作者
论文摘要
近年来，已经提出了基于深度学习的图像处理算法，包括图像超分辨率方法，其性能得到了显着改善。但是，它们的实施和评估是根据各种深度学习框架和各种评估标准散布的。在本文中，我们提出了一个名为SRZOO的超分辨率任务的集成存储库，以在一个地方提供最新的超分辨率模型。我们的存储库不仅提供了现有预培训模型的转换版本，还提供用于转换其他模型的文档和工具包。此外，SRZOO还提供了平台不可静止的图像重建工具，以获取超级分辨图像并评估到位的性能。它还为基于图像的高级研究和其他图像处理模型带来了扩展的机会。 GitHub上可公开使用软件，文档和预培训模型。
Deep learning-based image processing algorithms, including image super-resolution methods, have been proposed with significant improvement in performance in recent years. However, their implementations and evaluations are dispersed in terms of various deep learning frameworks and various evaluation criteria. In this paper, we propose an integrated repository for the super-resolution tasks, named SRZoo, to provide state-of-the-art super-resolution models in a single place. Our repository offers not only converted versions of existing pre-trained models, but also documentation and toolkits for converting other models. In addition, SRZoo provides platform-agnostic image reconstruction tools to obtain super-resolved images and evaluate the performance in place. It also brings the opportunity of extension to advanced image-based researches and other image processing models. The software, documentation, and pre-trained models are publicly available on GitHub.
