|TREND||DATASET||BEST METHOD||PAPER TITLE||PAPER||CODE||COMPARE|
As far as we know, this is the first neural network architecture that is able to outperform JPEG at image compression across most bitrates on the rate-distortion curve on the Kodak dataset images, with and without the aid of entropy coding.
We introduce a simple and efficient lossless image compression algorithm.
We fully exploit the hierarchical features from all the convolutional layers.
We propose the first practical learned lossless image compression system, L3C, and show that it outperforms the popular engineered codecs, PNG, WebP and JPEG 2000.
#2 best model for Image Compression on ImageNet32
During training, the auto-encoder makes use of the context model to estimate the entropy of its representation, and the context model is concurrently updated to learn the dependencies between the symbols in the latent representation.
Deep latent variable models have seen recent success in many data domains.
In order to show the effectiveness of our proposed JointIQ-Net, extensive experiments have been performed, and showed that the JointIQ-Net achieves a remarkable performance improvement in coding efficiency in terms of both PSNR and MS-SSIM, compared to the previous learned image compression methods and the conventional codecs such as VVC Intra (VTM 7. 1), BPG, and JPEG2000.