1.Deep Convolutional Network
嘿Learning a Deep Convolutional Network for Image Super-Resolution 原文链接.
嘿Image Super-Resolution Using Deep Convolutional Networks原文链接.
嘿Accurate Image Super-Resolution Using Very Deep Convolutional Networks原文链接.
嘿Deep Network Cascade for Image Super-resolution
2.Sparse Representation
嘿Image Super-Resolution Via Sparse Representation原文链接.
嘿On single image scale-up using sparse-representations原文链接.
嘿Single-Image Super-Resolution Using Sparse Regression and Natural Image Prior原文链接.
嘿Image super-resolution as sparse representation of raw image patches原文链接.
3. forests
嘿Fast and accurate image upscaling with super-resolution forests原文链接.
嘿Fast Image Interpolation via Random Forests
原文链接.
嘿SRHRF+: Self-Example Enhanced Single Image Super-Resolution Using. Hierarchical Random Forests原文链接.
4.dictionary
嘿Coupled Dictionary Training for Image Super-Resolution
嘿A Deep Dictionary Model for Image Super-Resolution
嘿Single face image super-resolution via solo dictionary learning
嘿Semi-Coupled Dictionary Learning with Applications to Image Super-Resolution and Photo-Sketch Image Synthesis原文链接.
嘿Single Image Super-resolution Using Gaussian Process Regression with Dictionary-based Sampling and Student-t Likelihood
5.neighbor embedding
嘿Low-complexity single-image super-resolution based on nonnegative
neighbor embedding原文链接.
嘿Super-resolution using neighbor embedding of back-projection residuals原文链接.
6. Regression
嘿Fast Image Super-Resolution Based on In-Place Example Regression
嘿Jointly Optimized Regressors for Image Super-resolution
嘿A+: Adjusted Anchored Neighborhood Regression for Fast Super-Resolution原文链接.
other
嘿Example-based super-resolution原文链接.
嘿Image super-resolution using gradient profile prior原文链接.
嘿Improving resolution by image registration原文链接.
嘿Learning Low-Level Vision原文链接.
评估方法
嘿Multiscale structural similarity for image quality assessment原文链接.
嘿Image quality assessment: from error visibility to structural similarity原文链接.
嘿Single-Image Super-Resolution: A Benchmark原文链接.