MLIC ++ : Linear Complexity Multi-Reference Entropy Modeling for Learned Image Compression
Top Cited Papers
Open Access
- 22 May 2025
- journal article
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Multimedia Computing, Communications, and Applications
- Vol. 21 (5) , 1-25
Abstract
The latent representation in learned image compression encompasses channel-wise, local spatial, and global spatial correlations, which are essential for the entropy model to capture for conditional entropy minimization. Efficiently capturing these contexts within a single entropy model, especially in high-resolution image coding, presents a challenge due to the computational complexity of existing global context modules. To address this challenge, we propose the Linear Complexity Multi-Reference Entropy Model (MEM \({}^{++}\) ). Specifically, the latent representation is partitioned into multiple slices. For channel-wise contexts, previously compressed slices serve as the context for compressing a particular slice. For local contexts, we introduce a shifted-window-based checkerboard attention module. This module ensures linear complexity without sacrificing performance. For global contexts, we propose a linear complexity attention mechanism. It captures global correlations by decomposing the softmax operation, enabling the implicit computation of attention maps from previously decoded slices. Using MEM++ as the entropy model, we develop the image compression method MLIC \({}^{++}\) . Extensive experimental results demonstrate that MLIC \({}^{++}\) achieves state-of-the-art performance, reducing BD-rate by \(13.39\%\) on the Kodak dataset compared to VTM-17.0 in Peak Signal-to-Noise Ratio (PSNR). Furthermore, MLIC \({}^{++}\) exhibits linear computational complexity and memory consumption with resolution, making it highly suitable for high-resolution image coding. Code and pre-trained models are available at https://github.com/JiangWeibeta/MLIC .
Keywords
All Related Versions
Funding Information
- Guangdong Provincial Key Laboratory of Ultra High Definition Immersive Media Technology (2024B1212010006)
- National Natural Science Foundation of China (U21B2012)
- Shenzhen Science and Technology Program-Shenzhen Cultivation of Excellent Scientific and Technological Innovation Talents project (RCJC20200714114435057)
- Outstanding Talents Training Fund in Shenzhen
This publication has 47 references indexed in Scilit:
- Swin Transformer: Hierarchical Vision Transformer using Shifted Windows2021
- Overview of the Versatile Video Coding (VVC) Standard and its ApplicationsIEEE Transactions on Circuits and Systems for Video Technology, 2021
- Causal Contextual Prediction for Learned Image CompressionIEEE Transactions on Circuits and Systems for Video Technology, 2021
- Nonlinear Transform CodingIEEE Journal of Selected Topics in Signal Processing, 2020
- Ensemble Learning-Based Rate-Distortion Optimization for End-to-End Image CompressionIEEE Transactions on Circuits and Systems for Video Technology, 2020
- Enhanced Deep Residual Networks for Single Image Super-Resolution2017
- Overview of the High Efficiency Video Coding (HEVC) StandardIEEE Transactions on Circuits and Systems for Video Technology, 2012
- ImageNet: A large-scale hierarchical image database2009
- Multiscale structural similarity for image quality assessment2004
- Overview of the H.264/AVC video coding standardIEEE Transactions on Circuits and Systems for Video Technology, 2003