Variational image compression with a scale hyperprior
Johannes Ballé, David Minnen, Saurabh Singh, Sung Jin Hwang, Nick Johnston
Code Available — Be the first to reproduce this paper.
ReproduceCode
- github.com/InterDigitalInc/CompressAIpytorch★ 1,540
- github.com/tensorflow/compressiontf★ 911
- github.com/FireFYF/SlimCAEtf★ 54
- github.com/mandt-lab/improving-inference-for-neural-image-compressiontf★ 53
- github.com/ipc-lab/NDICpytorch★ 35
- github.com/ipc-lab/DWSICpytorch★ 35
- github.com/jooyoungleeetri/scrtf★ 26
- github.com/klieberman/ood_nicpytorch★ 21
- github.com/gergely-flamich/relative-entropy-codingtf★ 19
- github.com/ipc-lab/ndic-campytorch★ 12
Abstract
We describe an end-to-end trainable model for image compression based on variational autoencoders. The model incorporates a hyperprior to effectively capture spatial dependencies in the latent representation. This hyperprior relates to side information, a concept universal to virtually all modern image codecs, but largely unexplored in image compression using artificial neural networks (ANNs). Unlike existing autoencoder compression methods, our model trains a complex prior jointly with the underlying autoencoder. We demonstrate that this model leads to state-of-the-art image compression when measuring visual quality using the popular MS-SSIM index, and yields rate-distortion performance surpassing published ANN-based methods when evaluated using a more traditional metric based on squared error (PSNR). Furthermore, we provide a qualitative comparison of models trained for different distortion metrics.