Exploration of Learned Lifting-Based Transform Structures for Fully Scalable and Accessible Wavelet-Like Image Compression

arXiv:2402.18761v1 Announce Type: cross
Abstract: This paper provides a comprehensive study on features and performance of different ways to incorporate neural networks into lifting-based wavelet-like transforms, within the context of fully scalable and accessible image compression. Specifically, we explore different arrangements of lifting steps, as well as various network architectures for learned lifting operators. Moreover, we examine the impact of the number of learned lifting steps, the number of channels, the number of layers and the support of kernels in …

abstract arxiv compression context cs.cv cs.mm eess.iv exploration explore features image networks neural networks paper performance scalable study type wavelet