Knowledge Commons of Institute of Automation,CAS
Ladder Pyramid Networks for Single Image Super-Resoluion | |
Mo, Zitao; He, Xiangyu; Li, Gang; Cheng, Jian | |
2020-10 | |
会议名称 | 27th IEEE International Conference on Image Processing |
会议日期 | October 25th-October28th |
会议地点 | Abudhabi |
出版者 | IEEE |
产权排序 | 1 |
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. |
关键词 | Ladder Pyramid Network, Lightweight Convolution, Super-Resolution |
收录类别 | EI |
语种 | 英语 |
七大方向——子方向分类 | 图像视频处理与分析 |
文献类型 | 会议论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/40125 |
专题 | 复杂系统认知与决策实验室_高效智能计算与学习 |
作者单位 | Institute of Automation, Chinese Academy of Sciences |
第一作者单位 | 中国科学院自动化研究所 |
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]:IEEE,2020. |
条目包含的文件 | 下载所有文件 | |||||
文件名称/大小 | 文献类型 | 版本类型 | 开放类型 | 使用许可 | ||
mo.pdf(355KB) | 会议论文 | 开放获取 | CC BY-NC-SA | 浏览 |
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。
修改评论