"Zero-Shot" Super-Resolution using Deep Internal Learning

被引:727
作者
Shocher, Assaf [1 ]
Cohen, Nadav [2 ]
Irani, Michal [1 ]
机构
[1] Weizmann Inst Sci, Dept Comp Sci & Appl Math, Rehovot, Israel
[2] Inst Adv Study, Sch Math, Princeton, NJ 08540 USA
来源
2018 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR) | 2018年
基金
以色列科学基金会;
关键词
D O I
10.1109/CVPR.2018.00329
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Deep Learning has led to a dramatic leap in Super Resolution (SR) performance in the past few years. However, being supervised, these SR methods are restricted to specific training data, where the acquisition of the low resolution (LR) images from their high-resolution (HR) counterparts is predetermined (e.g., bicubic downscaling), without any distracting artifacts (e.g., sensor noise, image compression, non-ideal PSF, etc). Real LI? images, however, rarely obey these restrictions, resulting in poor SR results by SotA (State of the Art) methods. In this paper we introduce "Zero-Shot" SR, which exploits the power of Deep Learning, but does not rely on prior training. We exploit the internal recurrence of information inside a single image, and train a small image-specific CNN at test time, on examples extracted solely from the input image itself. As such, it can adapt itself to different settings per image. This allows to perform SR of real old photos, noisy images, biological data, and other images where the acquisition process is unknown or non-ideal. On such images, our method outperforms SotA CNN-based SR methods, as well as previous unsupervised SR methods. To the best of our knowledge, this is the first unsupervised CNN-based SR method.
引用
收藏
页码:3118 / 3126
页数:9
相关论文
共 24 条
[1]  
[Anonymous], 2001, 8 IEEE INT C COMPUTE, DOI [DOI 10.1109/ICCV.2001.937655, 10.1109/ICCV.2001.937655]
[2]  
[Anonymous], CVPR
[3]  
Bahat Y, 2016, IEEE INT CONF COMPUT, P34
[4]  
Bahat Yuval, 2017, ICCV
[5]  
Chao Dong K. H. X. T., 2014, EUR C COMP VIS ECCV
[6]   Image and Video Upscaling from Local Self-Examples [J].
Freedman, Gilad ;
Fattal, Raanan .
ACM TRANSACTIONS ON GRAPHICS, 2011, 30 (02)
[7]  
Glasner S. B. D., 2009, ICCV
[8]  
Huang JB, 2015, PROC CVPR IEEE, P5197, DOI 10.1109/CVPR.2015.7299156
[9]   IMPROVING RESOLUTION BY IMAGE REGISTRATION [J].
IRANI, M ;
PELEG, S .
CVGIP-GRAPHICAL MODELS AND IMAGE PROCESSING, 1991, 53 (03) :231-239
[10]  
Kim J, 2016, PROC CVPR IEEE, P1637, DOI [10.1109/CVPR.2016.182, 10.1109/CVPR.2016.181]