Recently, neural network (NN)-based image compression studies have actively been made and has shown impressive performance in comparison to traditional methods. However, most of the works have focused on non-scalable image compression (single-layer coding) while spatially scalable image compression has drawn less attention although it has many applications. In this paper, we propose a novel NN-based spatially scalable image compression method, called COMPASS, which supports arbitrary-scale spatial scalability. Our proposed COMPASS has a very flexible structure where the number of layers and their respective scale factors can be arbitrarily determined during inference. To reduce the spatial redundancy between adjacent layers for arbitrary scale factors, our COMPASS adopts an inter-layer arbitrary scale prediction method, called LIFF, based on implicit neural representation. We propose a combined RD loss function to effectively train multiple layers. Experimental results show that our COMPASS achieves BD-rate gain of -58.33% and -47.17% at maximum compared to SHVC and the state-of-the-art NN-based spatially scalable image compression method, respectively, for various combinations of scale factors. Our COMPASS also shows comparable or even better coding efficiency than the single-layer coding for various scale factors.

翻译：近年来，基于神经网络（NN）的图像压缩研究已积极开展，与传统方法相比展现出令人印象深刻的性能。然而，大多数工作集中于非可扩展图像压缩（单层编码），而空间可扩展图像压缩尽管具有众多应用，却较少受到关注。本文提出了一种新颖的基于神经网络的空间可扩展图像压缩方法，称为COMPASS，其支持任意尺度的空间可扩展性。我们提出的COMPASS具有非常灵活的结构，其中层数及各层对应的尺度因子在推理过程中可任意确定。为减少任意尺度因子下相邻层间的空间冗余，我们的COMPASS采用了一种基于隐式神经表示的层间任意尺度预测方法LIFF。我们提出了一种组合RD损失函数来有效训练多层网络。实验结果表明，对于多种尺度因子组合，我们的COMPASS相较于SHVC和最先进的基于神经网络的空间可扩展图像压缩方法，分别实现了最大-58.33%和-47.17%的BD-rate增益。对于不同尺度因子，我们的COMPASS也显示出与单层编码相当甚至更优的编码效率。