Learned Lossless Image Compression with Combined Channel-conditioning Models and Autoregressive Modules

• Published in: IEEE access 2023-01, Vol.11, p.1-1
• Main Authors: Wang, Ran, Liu, Jinming, Sun, Heming, Katto, Jiro
• Format: Article
• Language: English
• Subjects: Algorithms; Autoregressive model; Autoregressive models; Channel-conditioning model; Computational modeling; Computer architecture; Context modeling; Data models; Decoding; Image coding; Image compression; Image enhancement; Learning; Lossless Image Compression; Quantization (signal); Redundancy
• ISSN: 2169-3536; 2169-3536
• DOI: 10.1109/ACCESS.2023.3291591

Lossless image compression is an important research field in image compression. Recently, learning-based lossless image compression methods achieved impressive performance compared with traditional lossless methods, such as WebP, JPEG2000, and FLIF. The aim of the lossless image compression algorithms is to use shorter codelength to represent images. To encode an image with fewer bytes, eliminating the redundancies among the pixels in the image is highly important. Hence, in this paper, we explore the idea of combining an autoregressive model for the raw images based on the end-to-end lossless architecture proposed to enhance the performance. Furthermore, inspired by the successful achievements of Channel-conditioning models, we propose a Multivariant Mixture distribution Channel-conditioning model (MMCC) in our network architecture to boost performance. The experimental results show that our approach outperforms most classical lossless compression methods and existing learning-based lossless methods.