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

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Vaisman, Amit, Ohayon, Guy, Manor, Hila, Elad, Michael, Michaeli, Tomer
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866908963584344064
author Vaisman, Amit
Ohayon, Guy
Manor, Hila
Elad, Michael
Michaeli, Tomer
author_facet Vaisman, Amit
Ohayon, Guy
Manor, Hila
Elad, Michael
Michaeli, Tomer
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2511_06424
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Turbo-DDCM: Fast and Flexible Zero-Shot Diffusion-Based Image Compression
Vaisman, Amit
Ohayon, Guy
Manor, Hila
Elad, Michael
Michaeli, Tomer
Image and Video Processing
Artificial Intelligence
Computer Vision and Pattern Recognition
Signal Processing
Machine Learning
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.
title Turbo-DDCM: Fast and Flexible Zero-Shot Diffusion-Based Image Compression
topic Image and Video Processing
Artificial Intelligence
Computer Vision and Pattern Recognition
Signal Processing
Machine Learning
url https://arxiv.org/abs/2511.06424