期刊
COMPUTER VISION - ECCV 2016, PT I
卷 9905, 期 -, 页码 628-644出版社
SPRINGER INTERNATIONAL PUBLISHING AG
DOI: 10.1007/978-3-319-46448-0_38
关键词
Compression artifacts reduction; Dual-domain representation; Very deep convolutional network
We propose a highly accurate approach to remove artifacts of JPEG-compressed images. Our approach jointly learns a very deep convolutional network in both DCT and pixel domains. The dual-domain representation can make full use of DCT-domain prior knowledge of JPEG compression, which is usually lacking in traditional network-based approaches. At the same time, it can also benefit from the prowess and the efficiency of the deep feed-forward architecture, in comparison to capacity-limited sparse-coding-based approaches. Two simple strategies, i.e., Adam and residual learning, are adopted to train the very deep network and later proved to be a success. Extensive experiments demonstrate the large improvements of our approach over the state of the arts.
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