Image Super-Resolution Based on Data-Driven Gaussian Process Regression

Learning local Gaussian process regression for image super-resolution

“…However, the feature representation has an important influence on the performance of super resolution reconstruction [21], so we detail how to represent an LR image patch. One basic feature is the patch itself, concatenating the column of a patch, which is used in our previous work [23]. However, we experimentally find that it is inferior to the gradient based feature according to the SR performance, which will be further discussed in Section 5.…”

“…PGPR is different from DDGPR which is proposed in [23] in the two major ways: 1) in DDGPR, the local GPR models are made for image patches, while in PGPR, the local GPR models are made for prototypes of image patches; 2) when an HR image is generated from its LR image, we need to build an image training dataset and learn a GPR model for each image patch in DDGPR, while in PGPR we just anchor an image patch to its nearest prototype and look up the corresponding prototype model which is pre-computed and stored as a reference model. The two differences lead to much fewer GPR models and significantly less computational time of the HR image reconstruction for PGPR than for DDGPR.…”

Learning Local Distribution for Extremely Efficient Single-Image Super-Resolution

“…Moreover, because the statistical priors cannot fit all samples, the optimization-based methods also suffer from poor robustness. With the development of machine learning, lots of data-driven methods have been proposed [9][10][11]. The sparse coding-based methods [12][13][14] introduce a learning-based encoder to sparsely encode both LR patches and HR patches and then try to build the mapping function from LR patches to HR patches with sparse representation.…”