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 each learned lifting operator. To facilitate the study, we investigate two generic training methodologies that are simultaneously appropriate to a wide variety of lifting structures considered. Experimental results ultimately suggest that retaining fixed lifting steps from the base wavelet transform is highly beneficial. Moreover, we demonstrate that employing more learned lifting steps and more layers in each learned lifting operator do not contribute strongly to the compression performance. However, benefits can be obtained by utilizing more channels in each learned lifting operator. Ultimately, the learned wavelet-like transform proposed in this paper achieves over 25% bit-rate savings compared to JPEG 2000 with compact spatial support.
Abstract (translated)
本文对将神经网络嵌入到基于提升的波浪变换中特征和性能进行了全面的探讨,并考虑了完全可扩展和可访问图像压缩的上下文。具体来说,我们研究了不同提升步数的安排以及各种学习提升操作网络架构。此外,我们还检查了每个学习提升操作中参数的数量、通道数量、层数和内核支持对压缩性能的影响。为了方便研究,我们研究了两种适用于各种提升结构的通用训练方法。实验结果最终表明,保留基于原始波浪变换的基本提升步日是高度有益的。此外,我们还证明了在每种学习提升操作中使用更多的学习步数和层数并不能显著提高压缩性能。然而,通过在每个学习提升操作中使用更多的通道,可以获得比JPEG 2000有更好的压缩性能。最终,本文提出的学波浪变换实现了与紧凑空间支持下的JPEG 2000超过25%的比特率节省。
URL
https://arxiv.org/abs/2402.18761