Papers › DDFM: Denoising Diffusion Model for Multi-Modality Image Fusion
DDFM: Denoising Diffusion Model for Multi-Modality Image Fusion
Zixiang Zhao, Haowen Bai, Yuanzhi Zhu, Jiangshe Zhang, Shuang Xu, Yulun Zhang, Kai Zhang, Deyu Meng, Radu Timofte, Luc van Gool
Multi-modality image fusion aims to combine different modalities to produce fused images that retain the complementary features of each modality, such as functional highlights and texture details. To leverage strong generative priors and address challenges such as unstable training and lack of interpretability for GAN-based generative methods, we propose a novel fusion algorithm based on the denoising diffusion probabilistic model (DDPM). The fusion task is formulated as a conditional generation problem under the DDPM sampling framework, which is further divided into an unconditional generation subproblem and a maximum likelihood subproblem. The latter is modeled in a hierarchical Bayesian manner with latent variables and inferred by the expectation-maximization (EM) algorithm. By integrating the inference solution into the diffusion sampling iteration, our method can generate high-quality fused images with natural image generative priors and cross-modality information from source images. Note that all we required is an unconditional pre-trained generative model, and no fine-tuning is needed. Our extensive experiments indicate that our approach yields promising fusion results in infrared-visible image fusion and medical image fusion. The code is available at https://github.com/Zhaozixiang1228/MMIF-DDFM.
In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.
Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.
For agents, on Syntology's MCP service (how to connect):
get_harvested_code_for_paper(arxiv_id="2303.06840")get_code(code_sha256="…")with a sample'scode_sha256from the list belowget_citation_path(paper_1="2303.06840", paper_2="…")with another paper's arXiv id or titleget_concepts_for_paper(arxiv_id="2303.06840")
Code
Syntology 27 code samples: 26 from 4 repositories linked to this paper, 1 identical to code harvested from another paper's repository. Across all 27: 18 ran (of which 14 constructed an object rather than computing a result; 15 with no instrument failure: 0 honoured, 0 violated, 15 with no contract checked; 3 where Syntology's instrument failed) · 9 unverified. Where Syntology's instrument failed: 1 where our contract draft was wrong; 2 where the contract check could not run; failures of Syntology's instrument, not of the code.
By repository: official repository: 5 samples from 1 repository, 3 ran (0 with no instrument failure; 3 where Syntology's instrument failed); community (archive-listed): 21 samples from 3 repositories, 15 ran (15 with no instrument failure; 0 where Syntology's instrument failed); 1 identical to code first harvested elsewhere. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.
Levels written between 2026-09-22 and 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.
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
27 samples harvested: 18 ran (of which 14 constructed an object rather than computing a result; 15 with no instrument failure: 0 honoured, 0 violated, 15 with no contract checked; 3 where Syntology's instrument failed) · 9 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.
Licence: 27 of the 27 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 4 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. 1 sample is listed last, in a group without a repository. “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. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. For 10 samples that ran, the graph records a signature this page does not show: for a class the fixture built without calling, the harness called the object with inputs it made up itself, so the recorded signature is the harness's probe, not the fixture's arguments. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.
Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (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 are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. 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 six 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; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. 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.
A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.
7f035f55e2f08711 · report
fixture: signature IR:Tensor/2/float · returned dict · level recorded 2026-09-22 500976c0521f9f77 · report
fixture: signature array:ndarray/3/float, time:int/0/int, target:Tensor/3/float · returned Tensor · level recorded 2026-09-22 15f0af0dcf7ed33b · report
fixture: signature psf:Tensor/2/float, outSize:tuple/1/int · returned Tensor · level recorded 2026-09-22 41504cc32fc4911f · report
0b97acea1e85e92b · report
census: 13 implementations from 12 papers, 10 distinct outputs across 4 buckets, one shared input per bucket net/Film.py ran · metamorphic tier: deterministic no licence file found · pointer only ·
98e962e3944f0fb6 · report
fixture: returned Attention · level recorded 2026-09-22 553a596819206f47 · report
fixture: returned CrossAttention · level recorded 2026-09-22 census: 5 implementations from 5 papers, 5 distinct outputs across 3 buckets, one shared input per bucket net/Film.py ran · metamorphic tier: deterministic no licence file found · pointer only ·
7b4409a2654eb25d · report
fixture: returned LayerNorm · level recorded 2026-09-22 19465fcfbb7556c2 · report
fixture: returned imagefeature2textfeature · level recorded 2026-09-22 efbaf56152135934 · report
fixture: returned text_preprocess · level recorded 2026-09-22 610a6372a350c17e · report
ea4e2e2f5875a2cc · report
4eb73bbf45be6872 · report
fixture: returned DetailFeatureExtraction · level recorded 2026-09-22 a4d094c84b651498 · report
fixture: returned DetailNode · level recorded 2026-09-22 6a741c9cce81776b · report
fixture: returned InvertedResidualBlock · level recorded 2026-09-22 dc2b3fa6c2ac9333 · report
fixture: returned Mlp · level recorded 2026-09-22 7fbefc76d724c861 · report
fixture: returned TransformerBlock · level recorded 2026-09-22 48e78dfab1e4912c · report
1d47b40725571522 · report
f68c09a19fb1adc5 · report
fixture: returned AttentionBase · level recorded 2026-09-22 ef9dcfa1656c7a2d · report
fixture: returned GlobalFeatureExtraction · level recorded 2026-09-22 47b15bbe9ab60e4b · report
fixture: returned LocalFeatureExtraction · level recorded 2026-09-22 d41e29922999d7fa · report
fixture: returned Mlp · level recorded 2026-09-22 census: 6 implementations from 5 papers, 6 distinct outputs across 2 buckets, one shared input per bucket nets/Ufuser.py ran fingerprinted no licence file found · pointer only ·
5efba677a3ddb846 · report
fixture: signature x:Tensor/4/float · returned Tensor · level recorded 2026-09-24 1fc84abe149bcb05 · report
1 sample is identical to code Syntology harvested from another paper's repository; this paper's own copy was not located, so no repository is named and no licence is recorded.
e92451e6fb900818 · report
Method as code Syntology
What Syntology's graph records as this paper's claimed method, lifted into code: each assembly names its bricks (functions and classes), each with its own role and its own verification level. An assembly is not a check that the code implements the method correctly or reproduces the paper's results. Levels are each brick's own verification level in Syntology's graph (level 0: no recorded run), listed brick by brick and never combined into one level; “ran” means the brick executed on a synthesized input, not that its output is correct, and the instrument figure counts failures of Syntology's instrument, not of the code. Where a model read the code against the paper's claim, each assembly's label verdict is one model's judgement, kept in this page's JSON twin; it is not calibrated, so no card prints it. Siblings are assemblies lifted from this paper in the same batch for the same method: alternative readings kept side by side; none replaces or supersedes another.
4 assemblies on this paper: 4 harvested, 0 generated, listed in 1 groups (siblings lifted in one batch form one group).
4 sibling assemblies for DDFM (harvested), lifted in the same batch on 2026-09-09: alternative readings kept side by side; none replaces or supersedes another.
harvested Assembly for DDFM (graph method: DDFM). 6 bricks; individually on a fixture: 3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 3 unverified. The assembly has not been run end-to-end.
one of 4 siblings
- GaussianDiffusion entry · level 0 · unverified ·
41504cc32fc4911f - EM_Initial helper · level 1 · ran · our draft was wrong ·
7f035f55e2f08711 - extract_and_expand helper · level 1 · ran; the contract check could not run (RAISES) ·
500976c0521f9f77 - get_mean_processor helper · level 0 · unverified ·
e92451e6fb900818 - get_var_processor helper · level 0 · unverified ·
0b97acea1e85e92b - psf2otf helper · level 1 · ran; the contract check could not run (RAISES) ·
15f0af0dcf7ed33b
harvested Assembly for DDFM (graph method: DDFM). 12 bricks; individually on a fixture: 10 ran (of which 8 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified. The assembly has not been run end-to-end.
one of 4 siblings
- Net entry · level 0 · unverified ·
610a6372a350c17e - restormer_cablock model · level 0 · unverified ·
ea4e2e2f5875a2cc - text_preprocess data_transform · level 1 · ran ·
efbaf56152135934 - CrossAttention model · level 1 · ran ·
553a596819206f47 - imagefeature2textfeature model · level 1 · ran ·
19465fcfbb7556c2 - Attention helper · level 1 · ran ·
98e962e3944f0fb6 - BiasFree_LayerNorm helper · level 1 · ran ·
db9f0e70f3f18049 - FeedForward helper · level 1 · ran ·
479ae430111a6061 - LayerNorm helper · level 1 · ran ·
7b4409a2654eb25d - WithBias_LayerNorm helper · level 1 · ran ·
1d90d30671b0d4b8 - to_3d helper · level 1 · ran; the contract check could not run ·
82a15cc1e46f7e4d - to_4d helper · level 1 · ran; the contract check could not run ·
b20f2a5df739a59e
harvested Assembly for DDFM (graph method: DDFM). 12 bricks; individually on a fixture: 10 ran (of which 7 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified. The assembly has not been run end-to-end.
one of 4 siblings
- Ufuser entry · level 0 · unverified ·
76102fd730986de1 - Restormer_CNN_block model · level 0 · unverified ·
1fc84abe149bcb05 - GlobalFeatureExtraction model · level 1 · ran ·
ef9dcfa1656c7a2d - LocalFeatureExtraction model · level 1 · ran ·
47b15bbe9ab60e4b - AttentionBase model · level 1 · ran ·
f68c09a19fb1adc5 - LayerNorm helper · level 1 · ran ·
7b4409a2654eb25d - Mlp model · level 1 · ran ·
d41e29922999d7fa - ResBlock model · level 1 · ran ·
5efba677a3ddb846 - BiasFree_LayerNorm helper · level 1 · ran ·
db9f0e70f3f18049 - WithBias_LayerNorm helper · level 1 · ran ·
1d90d30671b0d4b8 - to_3d helper · level 1 · ran; the contract check could not run ·
82a15cc1e46f7e4d - to_4d helper · level 1 · ran; the contract check could not run ·
b20f2a5df739a59e
harvested Assembly for DDFM (graph method: DDFM). 16 bricks; individually on a fixture: 14 ran (of which 12 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 0 violated, 12 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified. The assembly has not been run end-to-end.
one of 4 siblings
- Restormer_Encoder entry · level 0 · unverified ·
1d47b40725571522 - BaseFeatureExtraction helper · level 0 · unverified ·
48e78dfab1e4912c - DetailFeatureExtraction helper · level 1 · ran ·
4eb73bbf45be6872 - OverlapPatchEmbed model · level 1 · ran ·
099f2dc5f59fa05f - TransformerBlock model · level 1 · ran ·
7fbefc76d724c861 - AttentionBase helper · level 1 · ran ·
f68c09a19fb1adc5 - LayerNorm model · level 1 · ran ·
7b4409a2654eb25d - Mlp helper · level 1 · ran ·
dc2b3fa6c2ac9333 - DetailNode helper · level 1 · ran ·
a4d094c84b651498 - Attention model · level 1 · ran ·
98e962e3944f0fb6 - FeedForward model · level 1 · ran ·
479ae430111a6061 - BiasFree_LayerNorm helper · level 1 · ran ·
db9f0e70f3f18049 - WithBias_LayerNorm helper · level 1 · ran ·
1d90d30671b0d4b8 - to_3d helper · level 1 · ran; the contract check could not run ·
82a15cc1e46f7e4d - to_4d helper · level 1 · ran; the contract check could not run ·
b20f2a5df739a59e - InvertedResidualBlock helper · level 1 · ran ·
6a741c9cce81776b
Each brick ends with its code_sha256, Syntology's identity for that exact code; click one to copy the get_code call that returns it. For agents, on Syntology's MCP service: assembly(arxiv_id="2303.06840") returns these assemblies with each brick's role and wiring (how to connect).
Tasks
Results from the paper archive 2025-07-28
No leaderboard rows for this paper in the archive.
Methods
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