Improved Image Coding Autoencoder With Deep Learning
This is an incremental improvement for image compression applications, potentially enabling more efficient storage and transmission.
The paper tackles image compression by deepening an autoencoder network based on Ballé's approach, achieving a 4.0% reduction in bits per pixel and outperforming traditional methods like JPEG2000 by at least 20% in compression efficiency.
In this paper, we build autoencoder based pipelines for extreme end-to-end image compression based on Ballé's approach, which is the state-of-the-art open source implementation in image compression using deep learning. We deepened the network by adding one more hidden layer before each strided convolutional layer with exactly the same number of down-samplings and up-samplings. Our approach outperformed Ballé's approach, and achieved around 4.0% reduction in bits per pixel (bpp), 0.03% increase in multi-scale structural similarity (MS-SSIM), and only 0.47% decrease in peak signal-to-noise ratio (PSNR), It also outperforms all traditional image compression methods including JPEG2000 and HEIC by at least 20% in terms of compression efficiency at similar reconstruction image quality. Regarding encoding and decoding time, our approach takes similar amount of time compared with traditional methods with the support of GPU, which means it's almost ready for industrial applications.