Recently, learned image compression has achieved remarkable performance. The entropy model, which estimates the distribution of the latent representation, plays a crucial role in boosting rate-distortion performance. However, most entropy models only capture correlations in one dimension, while the latent representation contain channel-wise, local spatial, and global spatial correlations. To tackle this issue, we propose the Multi-Reference Entropy Model (MEM) and the advanced version, MEM$^+$. These models capture the different types of correlations present in latent representation. Specifically, We first divide the latent representation into slices. When decoding the current slice, we use previously decoded slices as context and employ the attention map of the previously decoded slice to predict global correlations in the current slice. To capture local contexts, we introduce two enhanced checkerboard context capturing techniques that avoids performance degradation. Based on MEM and MEM$^+$, we propose image compression models MLIC and MLIC$^+$. Extensive experimental evaluations demonstrate that our MLIC and MLIC+ models achieve state-of-the-art performance, reducing BD-rate by $8.05\%$ and $11.39\%$ on the Kodak dataset compared to VTM-17.0 when measured in PSNR.

翻译：近年来，学习型图像压缩取得了显著性能。用于估计潜变量分布的熵模型，在提升率失真性能方面起着关键作用。然而，大多数熵模型仅捕捉单一维度的相关性，而潜变量包含通道间、局部空间和全局空间三类相关性。为解决此问题，我们提出多参考熵模型（MEM）及其进阶版本MEM$^+$。这些模型能够捕捉潜变量中的不同类型相关性。具体而言，我们首先将潜变量分割为多个切片。在解码当前切片时，以先前解码的切片作为上下文，并利用先前解码切片的注意力图预测当前切片的全局相关性。为捕捉局部上下文，我们引入两种增强型棋盘格上下文捕获技术，避免性能退化。基于MEM和MEM$^+$，我们提出图像压缩模型MLIC和MLIC$^+$。大量实验评估表明，我们的MLIC和MLIC$^+$模型达到了业界领先性能，在Kodak数据集上以PSNR为指标，相较VTM-17.0分别降低了$8.05\%$和$11.39\%$的BD-rate。