Efficient Learned Wavelet Image and Video Coding

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Meyer, Anna, Prativadibhayankaram, Srivatsa, Kaup, André
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909378728165376
author Meyer, Anna
Prativadibhayankaram, Srivatsa
Kaup, André
author_facet Meyer, Anna
Prativadibhayankaram, Srivatsa
Kaup, André
contents Learned wavelet image and video coding approaches provide an explainable framework with a latent space corresponding to a wavelet decomposition. The wavelet image coder iWave++ achieves state-of-the-art performance and has been employed for various compression tasks, including lossy as well as lossless image, video, and medical data compression. However, the approaches suffer from slow decoding speed due to the autoregressive context model used in iWave++. In this paper, we show how a parallelized context model can be integrated into the iWave++ framework. Our experimental results demonstrate a speedup factor of over 350 and 240 for image and video compression, respectively. At the same time, the rate-distortion performance in terms of Bjøntegaard delta bitrate is slightly worse by 1.5\% for image coding and 1\% for video coding. In addition, we analyze the learned wavelet decomposition by visualizing its subband impulse responses.
format Preprint
id arxiv_https___arxiv_org_abs_2405_12631
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Efficient Learned Wavelet Image and Video Coding
Meyer, Anna
Prativadibhayankaram, Srivatsa
Kaup, André
Image and Video Processing
Learned wavelet image and video coding approaches provide an explainable framework with a latent space corresponding to a wavelet decomposition. The wavelet image coder iWave++ achieves state-of-the-art performance and has been employed for various compression tasks, including lossy as well as lossless image, video, and medical data compression. However, the approaches suffer from slow decoding speed due to the autoregressive context model used in iWave++. In this paper, we show how a parallelized context model can be integrated into the iWave++ framework. Our experimental results demonstrate a speedup factor of over 350 and 240 for image and video compression, respectively. At the same time, the rate-distortion performance in terms of Bjøntegaard delta bitrate is slightly worse by 1.5\% for image coding and 1\% for video coding. In addition, we analyze the learned wavelet decomposition by visualizing its subband impulse responses.
title Efficient Learned Wavelet Image and Video Coding
topic Image and Video Processing
url https://arxiv.org/abs/2405.12631