arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1810.04873cs.CV
收藏

用于图像超分辨率的深度双密度网络

Deep Bi-Dense Networks for Image Super-Resolution

Baidu Inc(百度公司);University of Technology Sydney(悉尼科技大学)

Yucheng Wang, Jialiang Shen, Jian Zhang

摘要:

本文提出了一种用于单图像超分辨率的深度双密度网络(DBDN)。我们的方法扩展了以前的块内密集连接方法,包括新的块间密集连接。这样,特征信息从单个密集块传播到所有后续块,而不是传播到单个后继块。为了构建DBDN,我们首先构建内部密集块,通过密集连接的卷积层和压缩层提取和压缩丰富的局部特征,以进行进一步的特征学习。然后,我们使用一个块间稠密网连接内部稠密块,这允许每个内部稠密块将其自身的局部特征传播给所有后继块。此外,我们的双密度构造将每个块连接到输出,减轻了训练中的消失梯度问题。我们提出的方法在五个基准数据集上的评估表明,我们的DBDN优于最先进的SISR与适度数量的网络参数。

英文摘要:

This paper proposes Deep Bi-Dense Networks (DBDN) for single image super-resolution. Our approach extends previous intra-block dense connection approaches by including novel inter-block dense connections. In this way, feature information propagates from a single dense block to all subsequent blocks, instead of to a single successor. To build a DBDN, we firstly construct intra-dense blocks, which extract and compress abundant local features via densely connected convolutional layers and compression layers for further feature learning. Then, we use an inter-block dense net to connect intra-dense blocks, which allow each intra-dense block propagates its own local features to all successors. Additionally, our bi-dense construction connects each block to the output, alleviating the vanishing gradient problems in training. The evaluation of our proposed method on five benchmark datasets shows that our DBDN outperforms the state of the art in SISR with a moderate number of network parameters.

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。

↑