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

2025-11-09

AI Summary

Existing zero-shot diffusion-based image compression methods suffer from slow inference and high computational overhead. To address this, we propose Turbo-DDCM, an efficient zero-shot compression framework built upon the Denoising Diffusion Codebook Model (DDCM). Our method introduces two key innovations: (i) a multi-noise vector fusion mechanism that injects substantial noise in a single denoising step, drastically reducing the number of iterative sampling steps; and (ii) an adaptive encoding protocol enabling region-priority coding and target PSNR-controllable compression. Turbo-DDCM requires no training—relying solely on reproducible random codebooks and zero-shot diffusion priors. Experiments demonstrate that Turbo-DDCM achieves 3–5× faster compression than prior zero-shot diffusion compressors while matching state-of-the-art PSNR and MS-SSIM performance. Moreover, it exhibits strong flexibility and adaptability across diverse compression scenarios.

Technology Category

• Computer Vision: Diffusion Models for Vision
• Data Mining & Knowledge Management: Data Compression
• Machine Learning: Learning on the Edge & Model Compression

Application Category

• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Search and Retrieval-Augmented AI: Efficiency and scalability of Web search engines
• User Modeling, Personalization and Recommendation: Federated recommendation systems and personalization

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.

Problem

• Accelerating slow diffusion-based image compression methods
• Reducing computational demands of zero-shot diffusion compression
• Providing flexible compression with region/quality control options

Innovation

• Fast zero-shot diffusion-based image compression method
• Combines multiple noise vectors per denoising step
• Flexible variants with priority and distortion control