KernelGAN: Blind Super Resolution Kernel Estimation using an Internal-GAN
1. 介紹 論文的出發點是要發掘patch上的自相關分佈，通過生成器G生成LR downsample後的版本和LR自己相應的patch在分佈上更相似（通過D網絡判別學到），從而學習出LR的降質過程，和ZSSR一樣，這個工作也是在單圖上進行訓練和測試，不同的是，這裏像ZSSR一樣使用bicubic作爲默認降質，而是利用GAN利用自身分佈去學習自己降質的過程。其中G網絡用來學習降採樣，當G網絡被訓練好
相關文章
- 1. Real-World Super-Resolution via Kernel Estimation and Noise Injection ---2020.08.10
- 2. Unpaired Image Super-Resolution using Pseudo-Supervision
- 3. -Zero-Shot-- Super-Resolution using Deep Internal Learning
- 4. CrossNet: An End-to-end Reference-based Super Resolution Network using Cross-scale Warping
- 5. Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural
- 6. 論文翻譯：2017_Audio super resolution using neural networks
- 7. (NIPS2020)Unfolding the Alternating Optimization for Blind Super Resolution 筆記
- 8. An Attention-Based Approach for Single Image Super Resolution
- 9. 《Image Super-Resolution Using Very Deep Residual Channel Attention Networks》
- 10. Image Super Resolution Using Conventional Neural Network (SRCNN)
- 更多相關文章...
- • Docker info 命令 - Docker命令大全
- • Thymeleaf項目實踐 - Thymeleaf 教程
- • RxJava操作符（六）Utility
- • RxJava操作符（一）Creating Observables
相關標籤/搜索
每日一句
-
每一个你不满意的现在，都有一个你没有努力的曾经。
歡迎關注本站公眾號,獲取更多信息
相關文章
- 1. Real-World Super-Resolution via Kernel Estimation and Noise Injection ---2020.08.10
- 2. Unpaired Image Super-Resolution using Pseudo-Supervision
- 3. -Zero-Shot-- Super-Resolution using Deep Internal Learning
- 4. CrossNet: An End-to-end Reference-based Super Resolution Network using Cross-scale Warping
- 5. Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural
- 6. 論文翻譯：2017_Audio super resolution using neural networks
- 7. (NIPS2020)Unfolding the Alternating Optimization for Blind Super Resolution 筆記
- 8. An Attention-Based Approach for Single Image Super Resolution
- 9. 《Image Super-Resolution Using Very Deep Residual Channel Attention Networks》
- 10. Image Super Resolution Using Conventional Neural Network (SRCNN)