Lossy Image Compression with Conditional Diffusion Models

TL;DR

This paper introduces a novel lossy image compression method using conditional diffusion models, outperforming GAN-based approaches and achieving competitive results with VAEs, with enhanced perceptual quality and efficient decoding.

Contribution

It presents a diffusion-based decoder for image compression that improves perceptual quality and decoding efficiency over existing neural compression methods.

Findings

Stronger FID scores than GAN-based models.

Competitive performance with VAE-based models on distortion metrics.

High-quality reconstructions with few decoding steps.

Abstract

This paper outlines an end-to-end optimized lossy image compression framework using diffusion generative models. The approach relies on the transform coding paradigm, where an image is mapped into a latent space for entropy coding and, from there, mapped back to the data space for reconstruction. In contrast to VAE-based neural compression, where the (mean) decoder is a deterministic neural network, our decoder is a conditional diffusion model. Our approach thus introduces an additional ``content'' latent variable on which the reverse diffusion process is conditioned and uses this variable to store information about the image. The remaining ``texture'' variables characterizing the diffusion process are synthesized at decoding time. We show that the model's performance can be tuned toward perceptual metrics of interest. Our extensive experiments involving multiple datasets and image quality assessment metrics show that our approach yields stronger reported FID scores than the GAN-based model, while also yielding competitive performance with VAE-based models in several distortion metrics. Furthermore, training the diffusion with $\mathcal{X}$-parameterization enables high-quality reconstructions in only a handful of decoding steps, greatly affecting the model's practicality. Our code is available at: \url{https://github.com/buggyyang/CDC_compression}