Papers › Compressed Image Generation with Denoising Diffusion Codebook Models

Compressed Image Generation with Denoising Diffusion Codebook Models

3 Feb 2025arXiv:2502.01189archive 2025-07-28

Guy Ohayon, Hila Manor, Tomer Michaeli, Michael Elad

We present a novel generative approach based on Denoising Diffusion Models (DDMs), which produces high-quality image samples along with their losslessly compressed bit-stream representations. This is obtained by replacing the standard Gaussian noise sampling in the reverse diffusion with a selection of noise samples from pre-defined codebooks of fixed iid Gaussian vectors. Surprisingly, we find that our method, termed Denoising Diffusion Codebook Model (DDCM), retains sample quality and diversity of standard DDMs, even for extremely small codebooks. We leverage DDCM and pick the noises from the codebooks that best match a given image, converting our generative model into a highly effective lossy image codec achieving state-of-the-art perceptual image compression results. More generally, by setting other noise selections rules, we extend our compression method to any conditional image generation task (e.g., image restoration), where the generated images are produced jointly with their condensed bit-stream representations. Our work is accompanied by a mathematical interpretation of the proposed compressed conditional generation schemes, establishing a connection with score-based approximations of posterior samplers for the tasks considered.

PaperPDFCodeCode Syntology ran

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2502.01189")

Code

Syntology Ran 10 of 20 code samples harvested from 1 repository linked to this paper; 10 have no recorded run. Of those that ran: 5 ran · our draft was wrong; 5 ran with no contract checked.

By repository: community (archive-listed): 20 samples from 1 repository, 10 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

20 samples harvested; 10 ran; 0 honoured the contract we drafted; 10 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

5ran · our draft was wrong
5ran
10unverified

Licence: 0 of the 20 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from DDCM-2025/ddcm-compressed-image-generation. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

load_yaml DDCM-2025/ddcm-compressed-image-generation/compressed_blind_face_restoration.py community (archive-listed) ran · our draft was wrong MIT (permissive) · 00c67a2ab9d4b104 · report
get_param_groups_and_shapes DDCM-2025/ddcm-compressed-image-generation/ddcm/guided_diffusion/fp16_util.py community (archive-listed) ran MIT (permissive) · e41367ad14ff58fd · report
make_master_params DDCM-2025/ddcm-compressed-image-generation/ddcm/guided_diffusion/fp16_util.py community (archive-listed) ran MIT (permissive) · e20dd5102da3b050 · report
register_mean_processor DDCM-2025/ddcm-compressed-image-generation/ddcm/guided_diffusion/posterior_mean_variance.py community (archive-listed) ran · our draft was wrong MIT (permissive) · 2423fa5313aa3525 · report
register_noise DDCM-2025/ddcm-compressed-image-generation/ddcm/guided_diffusion/measurements.py community (archive-listed) ran MIT (permissive) · 905f4b0d3baca742 · report
register_operator DDCM-2025/ddcm-compressed-image-generation/ddcm/guided_diffusion/measurements.py community (archive-listed) ran MIT (permissive) · 7f47ba486efd2c7e · report
register_sampler DDCM-2025/ddcm-compressed-image-generation/ddcm/guided_diffusion/gaussian_diffusion.py community (archive-listed) ran · our draft was wrong MIT (permissive) · d9bb4d03137bc7e9 · report
register_var_processor DDCM-2025/ddcm-compressed-image-generation/ddcm/guided_diffusion/posterior_mean_variance.py community (archive-listed) ran · our draft was wrong MIT (permissive) · e214ee19e7a9d92b · report
unflatten_master_params DDCM-2025/ddcm-compressed-image-generation/ddcm/guided_diffusion/fp16_util.py community (archive-listed) ran MIT (permissive) · 64fff1e30802b815 · report
zero_module DDCM-2025/ddcm-compressed-image-generation/ddcm/guided_diffusion/nn.py community (archive-listed) ran · our draft was wrong MIT (permissive) · 129b804760b3115f · report
avg_pool_nd DDCM-2025/ddcm-compressed-image-generation/ddcm/guided_diffusion/nn.py community (archive-listed) unverified MIT (permissive) · ecd0fc28815b65ae · report
cal_gradient_penalty DDCM-2025/ddcm-compressed-image-generation/ddcm/guided_diffusion/unet.py community (archive-listed) unverified MIT (permissive) · 944d16b22c6e6e77 · report
conv_nd DDCM-2025/ddcm-compressed-image-generation/ddcm/guided_diffusion/nn.py community (archive-listed) unverified MIT (permissive) · fe4eb545bbb728e0 · report
create_model DDCM-2025/ddcm-compressed-image-generation/ddcm/guided_diffusion/unet.py community (archive-listed) unverified MIT (permissive) · 5ee15cbb75da09af · report
create_sampler DDCM-2025/ddcm-compressed-image-generation/ddcm/guided_diffusion/gaussian_diffusion.py community (archive-listed) unverified MIT (permissive) · 7a9479e9edb0166b · report
get_loader DDCM-2025/ddcm-compressed-image-generation/ddcm/latent_runners.py community (archive-listed) unverified MIT (permissive) · 5550ef781c1cfd75 · report
get_mean_processor DDCM-2025/ddcm-compressed-image-generation/ddcm/guided_diffusion/posterior_mean_variance.py community (archive-listed) unverified MIT (permissive) · e92451e6fb900818 · report
get_operator DDCM-2025/ddcm-compressed-image-generation/ddcm/guided_diffusion/measurements.py community (archive-listed) unverified MIT (permissive) · bbb1be64bf961d18 · report
get_sampler DDCM-2025/ddcm-compressed-image-generation/ddcm/guided_diffusion/gaussian_diffusion.py community (archive-listed) unverified MIT (permissive) · b910fefa7866252e · report
resize DDCM-2025/ddcm-compressed-image-generation/compressed_blind_face_restoration.py community (archive-listed) unverified MIT (permissive) · 051480f785c72147 · report

Tasks

Conditional Image GenerationDenoisingDiversityImage CompressionImage GenerationImage Restoration

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Diffusion

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections