arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1605.00366cs.CV
收藏

基于卷积神经网络的压缩伪影消除

Compression Artifacts Removal Using Convolutional Neural Networks

Pavel Svoboda, Michal Hradis, David Barina, Pavel Zemcik

摘要:

本文表明,训练大型深度卷积神经网络(CNN)来减少JPEG压缩伪影是可能的,并且与以前使用的较小网络以及任何其他最先进的方法相比,这种网络可以提供更好的重建质量。我们能够通过结合残差学习、跳过架构和对称权重初始化,在相对较短的时间内单步的训练8层网络。我们通过评估三个不同的目标,相对于训练数据集大小的泛化,以及相对于JPEG质量水平的泛化,进一步深入了解卷积网络的JPEG伪影减少。

英文摘要:

This paper shows that it is possible to train large and deep convolutional neural networks (CNN) for JPEG compression artifacts reduction, and that such networks can provide significantly better reconstruction quality compared to previously used smaller networks as well as to any other state-of-the-art methods. We were able to train networks with 8 layers in a single step and in relatively short time by combining residual learning, skip architecture, and symmetric weight initialization. We provide further insights into convolution networks for JPEG artifact reduction by evaluating three different objectives, generalization with respect to training dataset size, and generalization with respect to JPEG quality level.

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。

↑