论文标题
基于注意的真实图像修复
Attention Based Real Image Restoration
论文作者
论文摘要
深度卷积神经网络在包含空间不变降解的图像上表现更好，也称为合成降解。但是，它们的性能受到真正衰减的照片的限制，需要多个阶段网络建模。为了推动恢复算法的实用性，本文提出了一种新型的单阶段盲目的真实图像恢复网络（r $^2 $ net），通过采用模块化体系结构。我们在残留结构上使用残差来简化低频信息的流量，并将功能注意力应用于利用信道依赖性。此外，对四个恢复任务的定量指标和视觉质量的评估，即对11个实际降级数据集的降级，超分辨率，去除雨滴和JPEG压缩，以针对30多种最先进的算法，这表明我们的R $ $^2 $网络的优势表明了我们的优势。我们还介绍了三个合成生成的降级数据集的比较，以展示我们方法在合成中降级的能力。代码，训练有素的模型和结果可在https://github.com/saeed-anwar/r2net上找到。
Deep convolutional neural networks perform better on images containing spatially invariant degradations, also known as synthetic degradations; however, their performance is limited on real-degraded photographs and requires multiple-stage network modeling. To advance the practicability of restoration algorithms, this paper proposes a novel single-stage blind real image restoration network (R$^2$Net) by employing a modular architecture. We use a residual on the residual structure to ease the flow of low-frequency information and apply feature attention to exploit the channel dependencies. Furthermore, the evaluation in terms of quantitative metrics and visual quality for four restoration tasks i.e. Denoising, Super-resolution, Raindrop Removal, and JPEG Compression on 11 real degraded datasets against more than 30 state-of-the-art algorithms demonstrate the superiority of our R$^2$Net. We also present the comparison on three synthetically generated degraded datasets for denoising to showcase the capability of our method on synthetics denoising. The codes, trained models, and results are available on https://github.com/saeed-anwar/R2Net.
