Ladder Pyramid Networks for Single Image Super-Resoluion
文献类型:会议论文
作者 | Mo, Zitao; He, Xiangyu; Li, Gang; Cheng, Jian |
出版日期 | 2020-10 |
会议日期 | October 25th-October28th |
会议地点 | Abudhabi |
关键词 | Ladder Pyramid Network, Lightweight Convolution, Super-Resolution |
英文摘要 | Benefiting from the powerful representation capability of convolutional neural networks, the performance of single image super-resolution (SISR) has been substantially improved in recent years. However, many current CNN-based methods are computation-intensive because of large-size intermediate feature maps and inefficient convolutions. To resolve these problems, we propose Ladder Pyramid Network (LPN) for single image super-resolution. Firstly, we use strided convolution to reduce the size of the intermediate feature maps and thus reducing computation burden. In order to better balance the effectiveness and efficiency, we propose Ladder Pyramid Module to gradually fuse hierarchical features to enhance performance. Secondly, lightweight convolution block similar to Inverted Residual Module of Mobilenet-v2 was introduced into SISR, with which we build the network backbone and ladder feature pyramid. Experimental results demonstrate that the proposed Ladder Pyramid Network can achieve comparable or better performance than previous lightweight networks while reducing the amount of computation. |
产权排序 | 1 |
会议录出版者 | IEEE |
语种 | 英语 |
源URL | [http://ir.ia.ac.cn/handle/173211/40125] |
专题 | 类脑芯片与系统研究 |
作者单位 | Institute of Automation, Chinese Academy of Sciences |
推荐引用方式 GB/T 7714 | Mo, Zitao,He, Xiangyu,Li, Gang,et al. Ladder Pyramid Networks for Single Image Super-Resoluion[C]. 见:. Abudhabi. October 25th-October28th. |
入库方式: OAI收割
来源:自动化研究所
其他版本
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。