点击次数：

论文类型：期刊论文

发表时间：2018-05-01

发表刊物：IEEE SIGNAL PROCESSING LETTERS

收录刊物：SCIE、EI

卷号：25

期号：5

页面范围：685-689

ISSN号：1070-9908

关键字：Information-compensated downsampling; pixel LSTM; receptive field; super-resolution

摘要：Alarge receptive field of deep networks can better incorporate image context and benefits image super-resolution (SR) in many ways. However, common techniques, like strided pooling and convolutional operations, are not directly applicable to SR due to severe image detail losses. In this letter, we circumvent this issue by proposing a new network architecture, namely the information-compensated (IC) downsampling block. It first uses pooling layers to downsample input feature maps and then immediately upsamples the feature maps back to the original size. To further compensate for information loss, skip connections are added to propagate lost features caused by downsampling to the upsampled output. In addition, pixelwise recurrent units are also applied to the downsampled feature maps to model context coherence. Compared with traditional pooling layers, the IC downsampling blocks cannot only enlarge receptive field and better capture image context, but also preserve image details, which are essential to SR. The final network consists of a stack of IC downsampling blocks and can be trained in an end-to-end manner. Experimental results verify that the proposed method performs favorably against the state-of-the-art approaches.