Koki Nakayama
ABSTRACT
Abstract— In this paper, we focus on a deep learning super-resolution method that can apply clear and natural digital zooming to captured images. We considered that a conventional ideal bicubic down-sampling dataset would be limited in the degradation space that could be handled, so we created a dataset by aligning images taken with different magnification lenses, eliminating pair images those were inappropriate for training, and changing the loss function. By using SwinIR in the super-resolution network as a magnification method, we succeeded in generating images those were more natural and sharper than conventional images.
- Xintao Wang, Ke Yu, Shixiang Wu, Jinjin Gu, Yihao Liu, Chao Dong, Yu Qiao and Chen Change Loy: “ESRGAN: Enhanced Super-Resolution Generative Adversarial Networks”, European Conference on Computer Vision (ECCV), pp.1-16, 2018.Google Scholar
- Ian Goodfellow, Jean Pouget-Abadie, Mehdi Mirza, Bing Xu, David Warde-Farley, Sherjil Ozair, Aaron Courville and Yoshua Bengio: “Generative Adversarial Nets”, Advances in Neural Information Processing Systems (NIPS), pp.1-9, 2014.Google Scholar
- Jingyun Liang, Jiezhang Cao, Guolei Sun, Kai Zhang, Luc Van Gool and Radu Timofte: “SwinIR: Image Restoration Using Swin Transformer”, International Conference on Computer Vision (ICCV), pp.1833-1844, 2021.Google ScholarCross Ref
- Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N. Gomez, Łukasz Kaiser and Illia Polosukhin: “Attention is all you need.”, Advances in Neural Information Processing Systems (NIPS), pp.1-11, 2017.Google Scholar
- Ze Liu, Yutong Lin, Yue Cao, Han Hu, Yixuan Wei, Zheng Zhang, Stephen Lin and Baining Guo: “Swin Transformer: Hierarchical Vision Transformer Using Shifted Windows”, International Conference on Computer Vision (ICCV), pp.10012-10022, 2021.Google ScholarCross Ref
- Chitwan Saharia, Jonathan Ho, William Chan, Tim Salimans, David J. Fleet and Mohammad Norouzi: “Image Super-Resolution via Iterative Refinement”, arXiv preprint arXiv:2104.07636v2, 2021.Google Scholar
- Jinjin Gu, Hannan Lu, Wangmeng Zuo and Chao Dong: “Blind Super-resolution with Iterative Kernel Correction”, Computer Vision and Pattern Recognition (CVPR), pp. 1604-1613, 2019.Google ScholarCross Ref
- Xuaner Zhang, Qifeng Chen, Ren Ng and Vladlen Koltun: “Zoom to Lean, Learn to Zoom”, Computer Vision and Pattern Recognition (CVPR), pp.3762-3770, 2019.Google Scholar
- Jianrui Cai, Hui Zeng, Hongwei Yong, Zisheng Cao and Lei New: “Toward Real-World Single Image Super-Resolution: A New Benchmark and A New Model”, International Conference on Computer Vision (ICCV), pp. 3086-3095, 2019.Google ScholarCross Ref
- Chang Chen, Zhiwei Xiong, Xinmei Tian, Zheng-Jun Zha and Feng Wu: “Camera Lens Super-Resolution”, Computer Vision and Pattern Recognition (CVPR), pp. 1652-1660, 2019.Google ScholarCross Ref
- Kai Zhang, Jingyun Liang, Luc Van Gool and Radu Timofte: “Designing a Practical Degradation Model for Deep Blind Image Super-Resolution”, International Conference on Computer Vision (ICCV), pp.4791-4800, 2021.Google ScholarCross Ref
- Xintao Wang, Liangbin Xie, Chao Dong and Ying Shan: “Real-ESRGAN: Training Real-World Blind Super-Resolution with Pure Synthetic Data”, International Conference on Computer Vision (ICCV), pp.1905-1914, 2021.Google ScholarCross Ref
- Shunta Maeda: “Unpaired Image Super-Resolution using Pseudo-Supervision”, Computer Vision and Pattern Recognition (CVPR), pp.291-300, 2020.Google ScholarCross Ref
- Longguang Wang, Yingqian Wang, Xiaoyu Dong, Qingyu Xu, Jungang Yang, Wei An and Yulan Guo: “Unsupervised Degradation Representation Learning for Blind Super-Resolution”, Computer Vision and Pattern Recognition (CVPR), pp.10581-10590, 2021.Google ScholarCross Ref
- Roey Mechrez, Itamar Talmi and Lihi Zelnik-Manor: “The Contextual Loss for Image Transformation with Non-Aligned Data”, European Conference on Computer Vision (ECCV), pp.768-783, 2018.Google ScholarDigital Library
- Karen Simonyan and Andrew Zisserman: “Very Deep Convolutional Networks for Large-scale Image Recognition”, arXiv preprint arXiv:1409.1556, 2014.Google Scholar
- Richard Zhang, Phillip Isola, Alexei A Efros, Eli Shechtman, and Oliver Wang: “The unreasonable effectiveness of deep features as a perceptual metric”, Computer Vision and Pattern Recognition (CVPR), pp.586-595, 2018.Google ScholarCross Ref
Recommendations
How Much Zoom is the Right Zoom from the Perspective of Super-Resolution?
ICVGIP '08: Proceedings of the 2008 Sixth Indian Conference on Computer Vision, Graphics & Image ProcessingConstructing a high-resolution (HR) image from low-resolution (LR) image(s) has been a very active research topic recently with focus shifting from multi-frames to learning based single-frame super-resolution (SR). Multi-frame SR algorithms attempt the ...
Edge-directed single image super-resolution via cross-resolution sharpening function learning
Edge-directed single image super-resolution methods have been paid more attentions due to their sharp edge preserving in the recovered high-resolution image. Their core is the high-resolution gradient estimation. In this paper, we propose a novel cross-...
Face image super-resolution through locality-induced support regression
In this paper we propose a novel face image super-resolution (SR) method named Locality-induced Support Regression (LiSR). Given a low-resolution (LR) input patch, we learn a mapping function between the local support LR and high-resolution (HR) patch ...
Comments