当前位置: X-MOL 学术Signal Process. Image Commun. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Enhanced wide-activated residual network for efficient and accurate image deblocking
Signal Processing: Image Communication ( IF 3.4 ) Pub Date : 2021-04-21 , DOI: 10.1016/j.image.2021.116283
Zhengxin Chen , Xiaohai He , Chao Ren , Pradeep Karn , Shuhua Xiong

To save bandwidth and storage space as well as speed up data transmission, people usually perform lossy compression on images. Although the JPEG standard is a simple and effective compression method, it usually introduces various visually unpleasing artifacts, especially the notorious blocking artifacts. In recent years, deep convolutional neural networks (CNNs) have seen remarkable development in compression artifacts reduction. Despite the excellent performance, most deep CNNs suffer from heavy computation due to very deep and wide architectures. In this paper, we propose an enhanced wide-activated residual network (EWARN) for efficient and accurate image deblocking. Specifically, we propose an enhanced wide-activated residual block (EWARB) as basic construction module. Our EWARB gives rise to larger activation width, better use of interdependencies among channels, and more informative and discriminative non-linearity activation features without more parameters than residual block (RB) and wide-activated residual block (WARB). Furthermore, we introduce an overlapping patches extraction and combination (OPEC) strategy into our network in a full convolution way, leading to large receptive field, enforced compatibility among adjacent blocks, and efficient deblocking. Extensive experiments demonstrate that our EWARN outperforms several state-of-the-art methods quantitatively and qualitatively with relatively small model size and less running time, achieving a good trade-off between performance and complexity.



中文翻译:

增强的广域激活残差网络,可实现高效,准确的图像解块

为了节省带宽和存储空间并加快数据传输速度,人们通常会对图像进行有损压缩。尽管JPEG标准是一种简单有效的压缩方法,但它通常会引入各种视觉上令人不悦的伪像,尤其是臭名昭著的分块伪像。近年来,深度卷积神经网络(CNN)在压缩伪像减少方面已取得了显着发展。尽管性能出色,但大多数深层CNN都因其深层和宽泛的体系结构而导致计算量大。在本文中,我们提出了一种增强的广域激活残差网络(EWARN),以实现高效,准确的图像解块。具体来说,我们提出了一种增强的广激活残差块(EWARB)作为基本构造模块。我们的EWARB产生了更大的激活宽度,更好地利用通道之间的相互依存关系,提供更多信息性和区分性的非线性激活功能,而没有比残差块(RB)和广泛激活的残差块(WARB)更多的参数。此外,我们以完全卷积的方式将重叠补丁提取和组合(OPEC)策略引入了我们的网络,从而导致了较大的接收场,相邻块之间的强制兼容性以及有效的解块。大量实验表明,我们的EWARN在数量和质量上均优于几种最新方法,并且模型尺寸相对较小,运行时间较少,从而在性能和复杂性之间取得了良好的折衷。以及更多信息性和区分性非线性激活功能,而没有比残差块(RB)和广泛激活的残差块(WARB)更多的参数。此外,我们以完全卷积的方式将重叠补丁提取和组合(OPEC)策略引入了我们的网络,从而导致了较大的接收场,相邻块之间的强制兼容性以及有效的解块。大量实验表明,我们的EWARN在数量和质量上均优于几种最新方法,并且模型尺寸相对较小,运行时间较少,从而在性能和复杂性之间取得了良好的折衷。以及更多信息性和区分性非线性激活功能,而没有比残差块(RB)和广泛激活的残差块(WARB)更多的参数。此外,我们以完全卷积的方式将重叠补丁提取和组合(OPEC)策略引入了我们的网络,从而导致了较大的接收场,相邻块之间的强制兼容性以及有效的解块。大量实验表明,我们的EWARN在数量和质量上均优于几种最新方法,并且模型尺寸相对较小,运行时间较少,从而在性能和复杂性之间取得了良好的折衷。增强相邻块之间的兼容性,以及有效的解块。大量实验表明,我们的EWARN在数量和质量上均优于几种最新方法,并且模型尺寸相对较小,运行时间较少,从而在性能和复杂性之间取得了良好的折衷。增强相邻块之间的兼容性,以及有效的解块。大量实验表明,我们的EWARN在数量和质量上均优于几种最新方法,并且模型尺寸相对较小,运行时间较少,从而在性能和复杂性之间取得了良好的折衷。

更新日期:2021-04-24
down
wechat
bug