The DOI matches its Crossref record; the references it cites are not checked yet.
Dif-Fusion: Toward High Color Fidelity in Infrared and Visible Image Fusion With Diffusion Models
Abstract
Color plays an important role in human visual perception, reflecting the spectrum of objects. However, the existing infrared and visible image fusion methods rarely explore how to handle multi-spectral/channel data directly and achieve high color fidelity. This paper addresses the above issue by proposing a novel method with diffusion models, termed as Dif-Fusion, to generate the distribution of the multi-channel input data, which increases the ability of multi-source information aggregation and the fidelity of colors. In specific, instead of converting multi-channel images into single-channel data in existing fusion methods, we create the multi-channel data distribution with a denoising network in a latent space with forward and reverse diffusion process. Then, we use the the denoising network to extract the multi-channel diffusion features with both visible and infrared information. Finally, we feed the multi-channel diffusion features to the multi-channel fusion module to directly generate the three-channel fused image. To retain the texture and intensity information, we propose multi-channel gradient loss and intensity loss. Along with the current evaluation metrics for measuring texture and intensity fidelity, we introduce Delta E as a new evaluation metric to quantify color fidelity. Extensive experiments indicate that our method is more effective than other state-of-the-art image fusion methods, especially in color fidelity. The source code is available at https://github.com/GeoVectorMatrix/Dif-Fusion.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“Recently, the emergence of diffusion models14–17 has brought a paradigm shift in the image generation field, with their exceptional generative capabilities demonstrating tremendous potential in LLIE tasks.”
From Temporally consistent low-light face video enhancement via video-to-video conditional diffusion (2026) · cites this paper as [16]
Citations
The citation lists are queued
They are fetched later and appear here then.
References 86 · Cited by 304
Research works printed but not linked: 4
- bandara, 2022, DDPM-CD: Remote sensing change detection using denoising diffusion probabilistic models, arXiv 2206 11892
- zimmermann, 2021, Score-based generative classifiers, arXiv 2110 00473
- baranchuk, 2021, Label-efficient semantic segmentation with diffusion models, Proc Int Conf Learn Represent (ICLR), 1
- daniels, 2021, Score-based generative neural networks for large-scale optimal transport, Proc Adv Neural Inf Process (NIPS), 34, 12955
Metadata
- Authors
- Yue, J., Fang, L., Xia, S., Deng, Y., & Ma, J.
- Affiliations
- Central South University (CN)
- Hunan University (CN)
- Changsha University of Science and Technology (CN)
- Beihang University (CN)
- Wuhan University (CN)
- Venue
- IEEE Transactions on Image Processing
- Published
- 2023
- Volume
- 32
- Pages
- 5705-5720
- ISSN
- 1057-7149 (ISSN-L)
- 1941-0042
- OpenAlex
- W4387682254
- Cited by
- 304
- References
- 86
- Citations by year
- 2026: 101 · 2025: 139 · 2024: 60 · 2023: 4
- FWCI
- 33.50
- Type
- journal article
- Language
- en
- Open access
- closed
- Licence
- Locations
- IEEE Transactions on Image Processing (publishedVersion)
- PubMed (publishedVersion)
- Funders
- National Natural Science Foundation of China (U22B2014, 62101072, 42201481)
- Science and Technology Plan Project Fund of Hunan Province (2022RSC3064)
- Hunan Provincial Natural Science Foundation of China (2021JJ40570, 2023JJ40024)
- Topics
- Physical Sciences › Engineering › Media Technology › Advanced Image Fusion Techniques
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Image Enhancement Techniques
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Image and Signal Denoising Methods
- Keywords
- infrared and visible image fusion, color fidelity, diffusion models, multi-channel fusion, intensity loss
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Dif-Fusion: Toward High Color Fidelity in Infrared and Visible Image Fusion With Diffusion Models. https://app.cochat.ai/papers/10.1109/tip.2023.3322046
- The paper
- Yue, J., Fang, L., Xia, S., Deng, Y., & Ma, J. (2023). Dif-Fusion: Toward High Color Fidelity in Infrared and Visible Image Fusion With Diffusion Models. IEEE Transactions on Image Processing. https://doi.org/10.1109/tip.2023.3322046
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.