超分辨率重建最新算法總結
Classical Sparse Coding Method
- ScSR
- Image super-resolution as sparse representation of raw image patches (CVPR2008), Jianchao Yang et al.
- 基於原始圖像塊稀疏表示的圖像超分辨率
- Image super-resolution via sparse representation (TIP2010), Jianchao Yang et al.
-
基於稀疏表示的圖像超分辨率
- Coupled dictionary training for image super-resolution (TIP2011), Jianchao Yang et al.
- 基於耦合字典訓練的圖像超分辨率重建
Anchored Neighborhood Regression Method
- ANR
- Anchored Neighborhood Regression for Fast Example-Based Super-Resolution (ICCV2013), Radu Timofte et al.
- 基於鄰域快速回歸的快速實例超分辨率
- A+
- A+: Adjusted Anchored Neighborhood Regression for Fast Super-Resolution (ACCV2014), Radu Timofte et al.
- IA
- Seven ways to improve example-based single image super resolution (CVPR2016), Radu Timofte et al.
Self-Exemplars
- SelfExSR
- Single Image Super-Resolution from Transformed Self-Exemplars (CVPR2015), Jia-Bin Huang et al.
Bayes
- NBSRF
- Naive Bayes Super-Resolution Forest (ICCV2015), Jordi Salvador et al.
- 樸素貝葉斯超分辨率森林
Deep Learning Method
- SRCNN
- Image Super-Resolution Using Deep Convolutional Networks (ECCV2014), Chao Dong et al.
- Image Super-Resolution Using Deep Convolutional Networks (TPAMI2015), Chao Dong et al.
- CSCN
- Deep Networks for Image Super-Resolution with Sparse Prior (ICCV2015), Zhaowen Wang et al.
- Robust Single Image Super-Resolution via Deep Networks with Sparse Prior (TIP2016), Ding Liu et al.
- VDSR
- Accurate Image Super-Resolution Using Very Deep Convolutional Networks (CVPR2016), Jiwon Kim et al.
- DRCN
- Deeply-Recursive Convolutional Network for Image Super-Resolution (CVPR2016), Jiwon Kim et al.
- 基於深度遞歸卷積網絡的圖像超分辨率重建
- ESPCN
- Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Network (CVPR2016), Wenzhe Shi et al.
- 基於高效亞像素卷積神經網絡的實時單圖像和視頻超分辨率
- Is the deconvolution layer the same as a convolutional layer?
- Checkerboard artifact free sub-pixel convolution
- FSRCNN
- Acclerating the Super-Resolution Convolutional Neural Network (ECCV2016), Dong Chao et al.
- LapSRN
- Deep Laplacian Pyramid Networks for Fast and Accurate Super-Resolution (CVPR 2017), Wei-Sheng Lai et al.
- 基於深拉普拉斯金字塔網絡的快速和準確的超分辨率
- EDSR
- Enhanced Deep Residual Networks for Single Image Super-Resolution (Winner of NTIRE2017 Super-Resolution Challenge), Bee Lim et al.
Perceptual Loss and GAN(損失函數上改進)
- Perceptual Loss
- Perceptual Losses for Real-Time Style Transfer and Super-Resolution (ECCV2016), Justin Johnson et al.
- 基於感知損失的實時風格轉移和超分辨率
- SRGAN
- Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network (CVPR2017), Christian Ledig et al.
- 基於生成對抗網絡的逼真圖片的單一圖像超分辨率
- AffGAN
- AMORTISED MAP INFERENCE FOR IMAGE SUPER-RESOLUTION (ICLR2017), Casper Kaae Sønderby et al.
- EnhanceNet
- EnhanceNet: Single Image Super-Resolution through Automated Texture Synthesis, Mehdi S. M. Sajjadi et al.
Video SR
- VESPCN
- Real-Time Video Super-Resolution with Spatio-Temporal Networks and Motion Compensation (CVPR2017), Jose Caballero et al.
- 來自
- https://github.com/huangzehao/Super-Resolution.Benckmark