AI Paper Atlas

Research map / Image generation / Image restoration

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

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

ICLR 2026 · Image generation › Image restoration · approach: Inverse imaging with learned priors · 2 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
combine many codebook atoms per step via closed-form thresholding instead of matching pursuitDDCM · Kodak24 round-trip timeseconds: 65 -> 1.8Improved
combine many atoms per step (Turbo-DDCM)DDCM · number of diffusion stepsreduction: more than 92% fewer stepsImproved
use combinatorial index bit protocol instead of ordered index encodingTurbo-DDCM · BPPBPP: ~40% lower BPPImproved
allow negative coefficients (sign selection) vs convex combinationTurbo-DDCM · representational capacityresidual approximationImproved
Turbo-DDCM vs DDCM at ~0.05 bppDDCM · Kodak24PSNR: 22.84 (0.046 bpp) -> 23.82 (0.058 bpp)Improved
Turbo-DDCM vs PSCPSC · Kodak24FID: 40.70 -> 25.75Improved
Turbo-DDCM vs DiffC at low bitrateDiffC · Kodak24FID: 26.39 (DiffC 0.057) vs 25.75 (Turbo 0.058)Mixed
Turbo-DDCM vs DiffC runtimeDiffC · Kodak24round-trip time (s): 11.23 -> 1.97Improved
increase bitrate to high regime due to SD 2.1 latent boundTurbo-DDCM · Kodak24 high bitratePSNRHurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy