期刊
IEEE ACCESS
卷 10, 期 -, 页码 1637-1649出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/ACCESS.2021.3138106
关键词
Image compression; convolutional neural network; generative adversarial network; weak connection; attention mechanism; dilated convolution
资金
- National Natural Science Foundation of China [61872280]
This paper proposes a weakly connected dense generative adversarial network, named WCDGAN, for artifacts removal of highly compressed images. Experimental results show that WCDGAN successfully removes compression artifacts and produces high-quality images.
In highly compressed images, i.e. quality factor q <= 10, JPEG compression causes severe compression artifacts including blocking, banding, ringing and color distortion. The compression artifacts seriously degrade image quality, which is not conducive to subsequent tasks, such as object detection and semantic segmentation. In this paper, we propose a weakly connected dense generative adversarial network for artifacts removal of highly compressed images, named WCDGAN. WCDGAN has three main ingredients of mixed convolution, weakly connected dense block (WCDB), and mixed attention. In the loss function, we add a perceptual loss to generate photo-realistic images with compression artifact removal. Experimental results show that WCDGAN successfully removes compression artifacts and produces sharp edges, clear textures and vivid colors even in highly compressed images. Moreover, WCDGAN outperforms state-of-the-art methods for compression artifact removal in terms of peak signal-to-noise ratio (PSNR) and structural similarity (SSIM).
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据