MLIC++: Linear Complexity Multi-Reference Entropy Modeling for Learned Image Compression

07/28/2023

∙

by   Wei Jiang, et al.

∙

0

∙

share

Recently, multi-reference entropy model has been proposed, which captures channel-wise, local spatial, and global spatial correlations. Previous works adopt attention for global correlation capturing, however, the quadratic cpmplexity limits the potential of high-resolution image coding. In this paper, we propose the linear complexity global correlations capturing, via the decomposition of softmax operation. Based on it, we propose the MLIC^++, a learned image compression with linear complexity for multi-reference entropy modeling. Our MLIC^++ is more efficient and it reduces BD-rate by 12.44 the Kodak dataset compared to VTM-17.0 when measured in PSNR. Code will be available at https://github.com/JiangWeibeta/MLIC.