为了 hyper prior entropy model、hierarchical prior 来看
来源
论文 https://arxiv.org/abs/1802.01436v2 复现 https://github.com/Hannah-Neumann/ai-image-compression
side information
"a concept universal to virtually all modern image codecs, but largely unexplored in image compression using artificial neural networks (ANNs)."
是指先验信息？ https://www.nxhh.net/qkwenda/3103389.html
Intro
本来是因为不了解 DCVC 提到的 prior 和 side information 来看，但这篇文章的 introduction 解答了我对图像压缩整体流程的很多疑问
甚至解释了一直没搞清楚的 entropy model（由编解码双方约定的被压缩信息的分布建模）
a joint, or even fully factorized, distribution
强调联合分布是？ factorized distribution是指？ 相关 https://zhuanlan.zhihu.com/p/380971473
Hyper prior
"Here, we use this formalism to show that side information can be viewed as a prior on the parameters of the entropy model, making them hyperpriors of the latent representation."
变分模型、变分推断
https://zhuanlan.zhihu.com/p/380971473