MLIC: Multi-Reference Entropy Model for Learned Image Compression

Abstract

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. Our code is available at https://github.com/JiangWeibeta/MLIC.

Accepted to ACMMM 2023

References in corpus (3)

• Contextformer: A Transformer with Spatio-Channel Attention for Context Modeling in Learned Image Compression
• A Cross Channel Context Model for Latents in Deep Image Compression
• DeepFGS: Fine-Grained Scalable Coding for Learned Image Compression

Cited by in corpus (6)

• MLIC++: Linear Complexity Multi-Reference Entropy Modeling for Learned Image Compression
• GroupedMixer: An Entropy Model with Group-wise Token-Mixers for Learned Image Compression
• ECVC: Exploiting Non-Local Correlations in Multiple Frames for Contextual Video Compression
• LLIC: Large Receptive Field Transform Coding with Adaptive Weights for Learned Image Compression
• LVC-LGMC: Joint Local and Global Motion Compensation for Learned Video Compression
• Spectral and Spatial Graph Learning for Multispectral Solar Image Compression