中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页 机构 成果 学者
  
  1. CAS IR Grid
  2. 自动化研究所
  3. 中国科学院自动化研究所
  4. 多模态人工智能系统全国重点实验室
End-to-End Alternating Optimization for Real-World Blind Super Resolution

文献类型：期刊论文

作者Luo, Zhengxiong1,2,4; Huang, Yan2,4; Li, Shang1,2; Wang, Liang2,3,4; Tan, Tieniu2,4,5
刊名INTERNATIONAL JOURNAL OF COMPUTER VISION
出版日期2023-08-03
页码18
ISSN号0920-5691
关键词Blind super resolution Degradation estimation Alternating optimization Restorer Estimator
DOI10.1007/s11263-023-01833-7
通讯作者Huang, Yan(yhuang@nlpr.ia.ac.cn)
英文摘要Blind super-resolution (SR) usually involves two sub-problems: (1) estimating the degradation of the given low-resolution (LR) image; (2) super-resolving the LR image to its high-resolution (HR) counterpart. Both problems are ill-posed due to the information loss in the degrading process. Most previous methods try to solve the two problems independently, but often fall into a dilemma: a good super-resolved HR result requires an accurate degradation estimation, which however, is difficult to be obtained without the help of original HR information. To address this issue, instead of considering these two problems independently, we adopt an alternating optimization algorithm, which can estimate the degradation and restore the SR image in a single model. Specifically, we design two convolutional neural modules, namely Restorer and Estimator. Restorer restores the SR image based on the estimated degradation, and Estimator estimates the degradation with the help of the restored SR image. We alternate these two modules repeatedly and unfold this process to form an end-to-end trainable network. In this way, both Restorer and Estimator could get benefited from the intermediate results of each other, and make each sub-problem easier. Moreover, Restorer and Estimator are optimized in an end-to-end manner, thus they could get more tolerant of the estimation deviations of each other and cooperate better to achieve more robust and accurate final results. Extensive experiments on both synthetic datasets and real-world images show that the proposed method can largely outperform state-of-the-art methods and produce more visually favorable results.
WOS关键词IMAGE SUPERRESOLUTION ; NETWORK ; DARK
WOS研究方向Computer Science
语种英语
出版者SPRINGER
WOS记录号WOS:001042003400001
源URL[http://ir.ia.ac.cn/handle/173211/53927]  
专题多模态人工智能系统全国重点实验室
通讯作者Huang, Yan
作者单位1.Univ Chinese Acad Sci, Artificial Intelligence Sch, Beijing 100049, Peoples R China
2.Chinese Acad Sci, Inst Automat, Beijing 100190, Peoples R China
3.Ctr Excellence Brain Sci & Intelligence Technol, Beijing, Peoples R China
4.Ctr Res Intelligent Percept & Comp, Beijing, Peoples R China
5.Nanjing Univ, Nanjing, Peoples R China
推荐引用方式
GB/T 7714		 Luo, Zhengxiong,Huang, Yan,Li, Shang,et al. End-to-End Alternating Optimization for Real-World Blind Super Resolution[J]. INTERNATIONAL JOURNAL OF COMPUTER VISION,2023:18.
APA Luo, Zhengxiong,Huang, Yan,Li, Shang,Wang, Liang,&Tan, Tieniu.(2023).End-to-End Alternating Optimization for Real-World Blind Super Resolution.INTERNATIONAL JOURNAL OF COMPUTER VISION,18.
MLA Luo, Zhengxiong,et al."End-to-End Alternating Optimization for Real-World Blind Super Resolution".INTERNATIONAL JOURNAL OF COMPUTER VISION (2023):18.

入库方式： OAI收割

来源：自动化研究所

浏览0
下载0
收藏0
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。