A Residual Diffusion Model for High Perceptual Quality Codec Augmentation
This work addresses the need for efficient, high-quality image compression tools, though it is incremental as it builds on existing diffusion models.
The paper tackled the problem of lossy compression for high-resolution images by introducing a diffusion-based codec (DIRAC) that enables smooth rate-distortion-perception tradeoff at test time, achieving competitive perceptual quality with GAN-based methods and reducing sampling steps to address computational cost.
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 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.