GHM Wavelet Transform for Deep Image Super Resolution
This work addresses image super-resolution for applications like satellite imaging and textures, but it is incremental as it builds on existing wavelet-based CNN methods.
The paper tackled image super-resolution by proposing the GHM multi-level discrete wavelet transform as preprocessing for convolutional neural networks, achieving higher quality reconstructions than single-level wavelets across three datasets including DIV2K, textures, and satellite images, with results evaluated using seven objective error measurements.
The GHM multi-level discrete wavelet transform is proposed as preprocessing for image super resolution with convolutional neural networks. Previous works perform analysis with the Haar wavelet only. In this work, 37 single-level wavelets are experimentally analyzed from Haar, Daubechies, Biorthogonal, Reverse Biorthogonal, Coiflets, and Symlets wavelet families. All single-level wavelets report similar results indicating that the convolutional neural network is invariant to choice of wavelet in a single-level filter approach. However, the GHM multi-level wavelet achieves higher quality reconstructions than the single-level wavelets. Three large data sets are used for the experiments: DIV2K, a dataset of textures, and a dataset of satellite images. The approximate high resolution images are compared using seven objective error measurements. A convolutional neural network based approach using wavelet transformed images has good results in the literature.