Neural Image Compression with a Diffusion-based Decoder

Noor Fathima Khanum Mohamed Ghouse, Jens Petersen, Auke J. Wiggers, Tianlin Xu, Guillaume Sautiere

Keywords: neural, image, lossy, compression, diffusion, gan, perceptual

TL;DR: Diffusion-based neural image codec allowing smooth and competitive rate-distortion-perception traversal at test time.

Abstract: Diffusion probabilistic models have recently achieved remarkable success in generating high quality image and video data. In this work, we build on this class of generative models and introduce a method for lossy compression of high resolution images. The resulting codec, which we call \emph{DIffuson-based Residual Augmentation Codec (DIRAC)}, is the first neural codec to allow smooth traversal of the rate-distortion-perception tradeoff at test time, while obtaining competitive performance with GAN-based methods in perceptual quality. Furthermore, while sampling from diffusion probabilistic models is notoriously expensive, we show that in the compression setting the number of steps can be drastically reduced.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

Submission Guidelines: Yes

Please Choose The Closest Area That Your Submission Falls Into: Generative models

Community Implementations: [ 1 code implementation](https://www.catalyzex.com/paper/arxiv:2301.05489/code)