Lossy Compression with Gaussian Diffusion
This addresses image compression for applications needing efficient transmission, offering a novel paradigm that supports progressive coding and arbitrary bitrates.
The paper tackles lossy image compression by using unconditional diffusion generative models (DiffC) to communicate corrupted pixels, achieving better performance than the state-of-the-art HiFiC on ImageNet 64x64 without an encoder transform.
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.