Practical Learned Lossless JPEG Recompression with Multi-Level Cross-Channel Entropy Model in the DCT Domain

03/30/2022
by   Lina Guo, et al.
0

JPEG is a popular image compression method widely used by individuals, data center, cloud storage and network filesystems. However, most recent progress on image compression mainly focuses on uncompressed images while ignoring trillions of already-existing JPEG images. To compress these JPEG images adequately and restore them back to JPEG format losslessly when needed, we propose a deep learning based JPEG recompression method that operates on DCT domain and propose a Multi-Level Cross-Channel Entropy Model to compress the most informative Y component. Experiments show that our method achieves state-of-the-art performance compared with traditional JPEG recompression methods including Lepton, JPEG XL and CMIX. To the best of our knowledge, this is the first learned compression method that losslessly transcodes JPEG images to more storage-saving bitstreams.

READ FULL TEXT
research
03/27/2023

Learned Image Compression with Mixed Transformer-CNN Architectures

Learned image compression (LIC) methods have exhibited promising progres...
research
08/30/2022

Learned Lossless Image Compression With Combined Autoregressive Models And Attention Modules

Lossless image compression is an essential research field in image compr...
research
07/18/2023

ECSIC: Epipolar Cross Attention for Stereo Image Compression

In this paper, we present ECSIC, a novel learned method for stereo image...
research
08/17/2023

Dynamic Kernel-Based Adaptive Spatial Aggregation for Learned Image Compression

Learned image compression methods have shown superior rate-distortion pe...
research
03/04/2022

Contextformer: A Transformer with Spatio-Channel Attention for Context Modeling in Learned Image Compression

Entropy modeling is a key component for high-performance image compressi...
research
03/05/2023

Learned Lossless Compression for JPEG via Frequency-Domain Prediction

JPEG images can be further compressed to enhance the storage and transmi...
research
01/30/2019

A study for Image compression using Re-Pair algorithm

The compression is an important topic in computer science which allows w...

Please sign up or login with your details

Forgot password? Click here to reset