Patch-based image Super Resolution using generalized Gaussian mixture model
This work addresses image enhancement for applications like photography or medical imaging, but it is incremental as it builds on existing patch-based and MMSE approaches.
The paper tackles the problem of single image super-resolution by learning a joint generalized Gaussian mixture model from low- and high-resolution patch pairs and reconstructing images using the minimum mean square error method, achieving competitive results with state-of-the-art methods.
Single Image Super Resolution (SISR) methods aim to recover the clean images in high resolution from low resolution observations.A family of patch-based approaches have received considerable attention and development. The minimum mean square error (MMSE) methodis a powerful image restoration method that uses a probability model on the patches of images. This paper proposes an algorithm to learn a jointgeneralized Gaussian mixture model (GGMM) from a pair of the low resolution patches and the corresponding high resolution patches fromthe reference data. We then reconstruct the high resolution image based on the MMSE method. Our numerical evaluations indicate that theMMSE-GGMM method competes with other state of the art methods.