arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2102.05105cs.CVcs.MMeess.IV
收藏

用于噪声图像的超分辨率的深度学习架构设计

Deep learning architectural designs for super-resolution of noisy images

IT Security Infrastructures Lab, University of Erlangen-N\"urnberg

Angel Villar-Corrales, Franziska Schirrmacher, Christian Riess

摘要:

深度学习的最新进展使单图像超分辨率(SR)研究得到了显着改进。然而,由于在上采样步骤期间噪声的放大,现有技术的方法通常无法从其低分辨率对应物的噪声版本重建高分辨率图像。然而,这对于来自未知相机的具有不可见类型的图像退化的图像尤其重要。在这项工作中,我们建议联合执行去噪和超分辨率。为此,我们研究了两种架构设计:“网络内”在特征级结合了这两项任务,而“预网络”首先执行去噪,然后执行超分辨率。我们的实验表明,这两种变体都具有特定的优势:对于任何降噪器的选择,当图像损坏的类型在训练和测试数据集中对齐时,网络内设计获得了最强的结果。预网络设计在看不见的图像损坏类型上表现出优越的性能,这是现有超分辨率模型的病理性失败情况。我们希望这些发现有助于实现超分辨率,也在不太受约束的情况下,源相机或成像条件没有得到很好的控制。源代码和预训练模型可在https://github.com/ angelvillar 96/超分辨率-noisy-images获得。

英文摘要:

Recent advances in deep learning have led to significant improvements in single image super-resolution (SR) research. However, due to the amplification of noise during the upsampling steps, state-of-the-art methods often fail at reconstructing high-resolution images from noisy versions of their low-resolution counterparts. However, this is especially important for images from unknown cameras with unseen types of image degradation. In this work, we propose to jointly perform denoising and super-resolution. To this end, we investigate two architectural designs: "in-network" combines both tasks at feature level, while "pre-network" first performs denoising and then super-resolution. Our experiments show that both variants have specific advantages: The in-network design obtains the strongest results when the type of image corruption is aligned in the training and testing dataset, for any choice of denoiser. The pre-network design exhibits superior performance on unseen types of image corruption, which is a pathological failure case of existing super-resolution models. We hope that these findings help to enable super-resolution also in less constrained scenarios where source camera or imaging conditions are not well controlled. Source code and pretrained models are available at https://github.com/ angelvillar96/super-resolution-noisy-images.

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。

↑