English

GHM Wavelet Transform for Deep Image Super Resolution

Image and Video Processing 2022-04-19 v1 Computer Vision and Pattern Recognition

Abstract

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.

Keywords

Cite

@article{arxiv.2204.07862,
  title  = {GHM Wavelet Transform for Deep Image Super Resolution},
  author = {Ben Lowe and Hadi Salman and Justin Zhan},
  journal= {arXiv preprint arXiv:2204.07862},
  year   = {2022}
}

Comments

13 pages

R2 v1 2026-06-24T10:50:00.683Z