From general to specific: Online updating for blind super-resolution | |
Li, Shang1,2![]() ![]() ![]() ![]() ![]() ![]() | |
发表期刊 | Pattern Recognition
![]() |
ISSN | 0031-3203 |
2022 | |
卷号 | 127期号:2022页码:108613 |
摘要 | Most deep learning-based super-resolution (SR) methods are not image-specific: 1) They are trained on samples synthesized by predefined degradations (e.g.bicubic downsampling), regardless of the domain gap between training and testing data. 2) During testing, they super-resolve all images by the same set of model weights, ignoring the degradation variety. As a result, most previous methods may suffer a performance drop when the degradations of test images are unknown and various (i.e.the case of blind SR). To address these issues, we propose an online SR (ONSR) method. It does not rely on predefined degradations and allows the model weights to be updated according to the degradation of the test image. Specifically, ONSR consists of two branches, namely internal branch (IB) and external branch (EB). IB could learn the specific degradation of the given test LR image, and EB could learn to super resolve images degraded by the learned degradation. In this way, ONSR could customize a specific model for each test image, and thus get more robust to various degradations. Extensive experiments on both synthesized and real-world images show that ONSR can generate more visually favorable SR results and achieve state-ofthe-art performance in blind SR. |
关键词 | Blind super-resolution Online updating Internal learning External learning |
DOI | 10.1016/j.patcog.2022.108613 |
收录类别 | SCI |
语种 | 英语 |
资助项目 | National Key R&D Program of China[2019YFB1406200] ; research achievement of the Key Laboratory of Digital Rights Services |
项目资助者 | National Key R&D Program of China ; research achievement of the Key Laboratory of Digital Rights Services |
WOS研究方向 | Computer Science ; Engineering |
WOS类目 | Computer Science, Artificial Intelligence ; Engineering, Electrical & Electronic |
WOS记录号 | WOS:000784335600002 |
出版者 | ELSEVIER SCI LTD |
七大方向——子方向分类 | 图像视频处理与分析 |
国重实验室规划方向分类 | 视觉信息处理 |
是否有论文关联数据集需要存交 | 否 |
引用统计 | |
文献类型 | 期刊论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/47446 |
专题 | 数字内容技术与服务研究中心_版权智能与文化计算 |
通讯作者 | Liu, Jie |
作者单位 | 1.Institute of Automation, Chinese Academy of Sciences 2.University of Chinese Academy of Sciences |
第一作者单位 | 中国科学院自动化研究所 |
通讯作者单位 | 中国科学院自动化研究所 |
推荐引用方式 GB/T 7714 | Li, Shang,Zhang, Guixuan,Luo, Zhengxiong,et al. From general to specific: Online updating for blind super-resolution[J]. Pattern Recognition,2022,127(2022):108613. |
APA | Li, Shang,Zhang, Guixuan,Luo, Zhengxiong,Liu, Jie,Zeng, Zhi,&Zhang, Shuwu.(2022).From general to specific: Online updating for blind super-resolution.Pattern Recognition,127(2022),108613. |
MLA | Li, Shang,et al."From general to specific: Online updating for blind super-resolution".Pattern Recognition 127.2022(2022):108613. |
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 | ||
PR.pdf(4880KB) | 期刊论文 | 作者接受稿 | 开放获取 | CC BY-NC-SA | 浏览 下载 |
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