2020/08/24 by Leonhard Helminger, Abdelaziz Djelouah, Helminger, Leonhard +6 · 22 citations
Computer Science · #Advanced Data Compression Techniques #Advanced Image Processing Techniques #Algorithm #Artificial intelligence #Computer Vision and Pattern Recognition (cs.CV) #Computer science #Computer vision #Data compression #Data compression ratio #FOS: Computer and information sciences #Image (mathematics) #Image and Signal Denoising Methods #Image compression #Image processing #Image quality #Lossless compression #Lossy compression #Quantization (signal processing) #Theoretical computer science #cs.CV
paper · pdf · doi:10.48550/arxiv.2008.10486
published in arXiv (Cornell University) (Cornell University)
arxiv created 2020/08/24 · openalex publication_date 2020/08/24 · arxiv updated 2020/08/25 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
Deep learning based image compression has recently witnessed exciting progress and in some cases even managed to surpass transform coding based approaches that have been established and refined over many decades. However, state-of-the-art solutions for deep image compression typically employ autoencoders which map the input to a lower dimensional latent space and thus irreversibly discard information already before quantization. Due to that, they inherently limit the range of quality levels that can be covered. In contrast, traditional approaches in image compression allow for a larger range of quality levels. Interestingly, they employ an invertible transformation before performing the quantization step which explicitly discards information. Inspired by this, we propose a deep image compression method that is able to go from low bit-rates to near lossless quality by leveraging normalizing flows to learn a bijective mapping from the image space to a latent representation. In addition to this, we demonstrate further advantages unique to our solution, such as the ability to maintain constant quality results through re-encoding, even when performed multiple times. To the best of our knowledge, this is the first work to explore the opportunities for leveraging normalizing flows for lossy image compression.