Neural Network Assisted Lifting Steps For Improved Fully Scalable Lossy Image Compression in JPEG 2000

arXiv:2403.01647v1 Announce Type: new
Abstract: This work proposes to augment the lifting steps of the conventional wavelet transform with additional neural network assisted lifting steps. These additional steps reduce residual redundancy (notably aliasing information) amongst the wavelet subbands, and also improve the visual quality of reconstructed images at reduced resolutions. The proposed approach involves two steps, a high-to-low step followed by a low-to-high step. The high-to-low step suppresses aliasing in the low-pass band by using the detail bands at the …

abstract arxiv compression cs.cv eess.iv image information network neural network quality reduce redundancy residual scalable type visual wavelet work