Self-tuned deep super resolution
作者： Zhangyang Wang , Yingzhen Yang , Zhaowen Wang , Shiyu Chang , Wei Han
DOI: 10.1109/CVPRW.2015.7301266
关键词: Deep learning 、 Reliability (computer networking) 、 Autoencoder 、 Range (mathematics) 、 Artificial intelligence 、 Image resolution 、 Convolutional code 、 Joint (audio engineering) 、 Computer vision 、 Computer science 、 Algorithm 、 Superresolution 、 Noise reduction
摘要: Deep learning has been successfully applied to image super resolution (SR). In this paper, we propose a deep joint (DJSR) model exploit both external and self similarities for SR. A Stacked Denoising Convolutional Auto Encoder (SDCAE) is first pre-trained on examples with proper data augmentations. It then fine-tuned multi-scale from each input, where the reliability of explicitly taken into account. We also enhance performance by sub-model training selection. The DJSR extensively evaluated compared state-of-the-arts, show noticeable improvements quantitatively perceptually wide range images.
harvard.edu
elsevier.com
sci-hub.se 参考文章(27)
Yoshua Bengio, Xavier Glorot, Antoine Bordes, Antoine Bordes, Domain Adaptation for Large-Scale Sentiment Classification: A Deep Learning Approach international conference on machine learning. pp. 513- 520 ,(2011)
Harold Christopher Burger, Christian Schuler, Stefan Harmeling, Learning How to Combine Internal and External Denoising Methods german conference on pattern recognition. pp. 121- 130 ,(2013) , 10.1007/978-3-642-40602-7_13
Chao Dong, Chen Change Loy, Kaiming He, Xiaoou Tang, Learning a Deep Convolutional Network for Image Super-Resolution european conference on computer vision. pp. 184- 199 ,(2014) , 10.1007/978-3-319-10593-2_13
Zhen Cui, Hong Chang, Shiguang Shan, Bineng Zhong, Xilin Chen, Deep Network Cascade for Image Super-resolution Computer Vision – ECCV 2014. pp. 49- 64 ,(2014) , 10.1007/978-3-319-10602-1_4
Chih-Yuan Yang, Jia-Bin Huang, Ming-Hsuan Yang, Exploiting self-similarities for single frame super-resolution asian conference on computer vision. pp. 497- 510 ,(2010) , 10.1007/978-3-642-19318-7_39
Pooya Khorrami, Tom Le Paine, Wei Han, Thomas S. Huang, An Analysis of Unsupervised Pre-training in Light of Recent Advances arXiv: Computer Vision and Pattern Recognition. ,(2014)
Jianchao Yang, Yingzhen Yang, Zhangyang Wang, Thomas S. Huang, Designing A Composite Dictionary Adaptively From Joint Examples arXiv: Computer Vision and Pattern Recognition. ,(2015)
D. Dai, R. Timofte, L. Van Gool, Jointly Optimized Regressors for Image Super-resolution Computer Graphics Forum. ,vol. 34, pp. 95- 104 ,(2015) , 10.1111/CGF.12544
I. Mosseri, M. Zontak, M. Irani, Combining the power of Internal and External denoising international conference on computational photography. pp. 1- 9 ,(2013) , 10.1109/ICCPHOT.2013.6528298
Gilad Freedman, Raanan Fattal, Image and video upscaling from local self-examples ACM Transactions on Graphics. ,vol. 30, pp. 1- 11 ,(2011) , 10.1145/1944846.1944852