In recent deep image compression neural networks, the entropy model plays a critical role in estimating the prior distribution of deep image encodings. Existing methods combine hyperprior with local context in the entropy estimation function. This greatly limits their performance due to the absence of a global vision. In this work, we propose a novel Global Reference Model for image compression to effectively leverage both the local and the global context information, leading to an enhanced compression rate. The proposed method scans decoded latents and then finds the most relevant latent to assist the distribution estimating of the current latent. A by-product of this work is the innovation of a mean-shifting GDN module that further improves the performance. Experimental results demonstrate that the proposed model outperforms the rate-distortion performance of most of the state-of-the-art methods in the industry.

翻译：在最近的深图像压缩神经网络中, 酶模型在估计深图像编码先前分布情况方面发挥着关键作用。 现有的方法将超前和本地环境结合到英特罗普估计功能中。 由于缺乏全球视野,这极大地限制了它们的性能。 在这项工作中, 我们提出了一个新的全球图像压缩参考模型, 以便有效地利用本地和全球背景信息, 从而导致提高压缩率。 拟议的方法扫描了已解码的潜伏, 并发现最相关的潜伏, 有助于当前潜伏的分布估计。 这项工作的一个副产品是, 以中位转换的GDN模块进行创新, 以进一步改进性能。 实验结果显示, 拟议的模型优于该行业大多数最新方法的率扭曲性能。