Turbo-DDCM: Fast and Flexible Zero-Shot Diffusion-Based Image Compression

Amit Vaisman, Guy Ohayon, Hila Manor, Michael Elad, Tomer Michaeli

Keywords: image compression, diffusion models, diffusion-based image compression, zero-shot diffusion-based image compression

TL;DR: We present Turbo-DDCM, a zero-shot diffusion-based image compression method up to an order of magnitude faster than state-of-the-art, while maintaining competitive compression quality. We also introduce prioritized regions compression for our method.

Abstract: While zero-shot diffusion-based compression methods have seen significant progress in recent years, they remain notoriously slow and computationally demanding. This paper presents an efficient zero-shot diffusion-based compression method that runs substantially faster than existing methods, while maintaining performance that is on par with the state-of-the-art techniques. Our method builds upon the recently proposed Denoising Diffusion Codebook Models (DDCMs) compression scheme. Specifically, DDCM compresses an image by sequentially choosing the diffusion noise vectors from reproducible random codebooks, guiding the denoiser’s output to reconstruct the target image. We modify this framework with *Turbo-DDCM*, which efficiently combines a large number of noise vectors at each denoising step, thereby significantly reducing the number of required denoising operations. This modification is also coupled with an improved encoding protocol. Furthermore, we introduce two flexible variants of Turbo-DDCM, a priority-aware variant that prioritizes user-specified regions and a distortion-controlled variant that compresses an image based on a target PSNR rather than a target BPP. Comprehensive experiments position Turbo-DDCM as a compelling, practical, and flexible image compression scheme.

Primary Area: generative models

Submission Number: 5666