Abstract
Currently, there is a high demand for neural network-based image compression codecs. These codecs employ non-linear transforms to create compact bit representations and facilitate faster coding speeds on devices compared to the hand-crafted transforms used in classical frameworks. The scientific and industrial communities are highly interested in these properties, leading to the standardization effort of JPEG-AI. The JPEG-AI verification model has been released and is currently under development for standardization. Utilizing neural networks, it can outperform the classic codec VVC intra by over 10% BD-rate operating at base operation point. Researchers attribute this success to the flexible bit distribution in the spatial domain, in contrast to VVC intra's anchor that is generated with a constant quality point. However, our study reveals that VVC intra displays a more adaptable bit distribution structure through the implementation of various block sizes. As a result of our observations, we have proposed a spatial bit allocation method to optimize the JPEG-AI verification model's bit distribution and enhance the visual quality. Furthermore, by applying the VVC bit distribution strategy, the objective performance of JPEG-AI verification mode can be further improved, resulting in a maximum gain of 0.45 dB in PSNR-Y.
Abstract (translated)
目前，基于神经网络的图像压缩码族具有很高需求。这些码族采用非线性变换来创建紧凑的位表示，与经典框架中使用的 hand-crafted 变换相比，有助于在设备上实现更快的编码速度。科学和工业界对这些特性非常感兴趣，导致了 JPEG-AI 的标准化努力。JPEG-AI 验证模型已经发布，目前正在标准化过程中。利用神经网络，它可以在基操作点上比经典编码 VVC 快超过 10% 的 BD-rate。研究人员认为，这一成功是因为在空间域中具有灵活的位分布，而 VVC 中的锚定点是使用常定质量点产生的。然而，我们的研究显示，通过实现各种块大小，VVC 中的位分布结构更加灵活。因此，我们提出了一个空间位分配方法，以优化 JPEG-AI 验证模型的位分布并提高视觉效果。此外，通过应用 VVC 位分布策略，JPEG-AI 验证模式的客观性能可以进一步优化，实现 PSNR-Y 最大增益为 0.45 dB。
URL
https://arxiv.org/abs/2402.17470
