2018/02/01 by Johannes Ballé, Ballé, Johannes, David Minnen +7 · 180 citations
Computer Science · Engineering · Mathematics · #Advanced Data Compression Techniques #Advanced Image Processing Techniques #FOS: Computer and information sciences #FOS: Electrical engineering #Image and Signal Denoising Methods #Image and Video Processing (eess.IV) #Information Theory (cs.IT) #cs.IT #eess.IV #electronic engineering #information engineering #math.IT
paper · pdf · doi:10.48550/arxiv.1802.01436
accepted as a conference contribution to International Conference on Learning Representations 2018
openalex publication_date 2018/02/01 · arxiv created 2018/05/01 · arxiv updated 2018/05/02 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
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.