Lossy Compression with Gaussian Diffusion

TL;DR

This paper introduces DiffC, a novel lossy image compression method using Gaussian diffusion models, which outperforms existing techniques like HiFiC on ImageNet 64x64 and supports progressive decoding.

Contribution

It presents a new diffusion-based compression approach that eliminates the need for traditional transform coding, demonstrating superior performance and theoretical insights.

Findings

Outperforms HiFiC on ImageNet 64x64

Supports progressive coding from partial bit streams

Flow-based reconstruction achieves 3 dB gain at high bitrates

Abstract

We consider a novel lossy compression approach based on unconditional diffusion generative models, which we call DiffC. Unlike modern compression schemes which rely on transform coding and quantization to restrict the transmitted information, DiffC relies on the efficient communication of pixels corrupted by Gaussian noise. We implement a proof of concept and find that it works surprisingly well despite the lack of an encoder transform, outperforming the state-of-the-art generative compression method HiFiC on ImageNet 64x64. DiffC only uses a single model to encode and denoise corrupted pixels at arbitrary bitrates. The approach further provides support for progressive coding, that is, decoding from partial bit streams. We perform a rate-distortion analysis to gain a deeper understanding of its performance, providing analytical results for multivariate Gaussian data as well as theoretic bounds for general distributions. Furthermore, we prove that a flow-based reconstruction achieves a 3 dB gain over ancestral sampling at high bitrates.