CoChat

Glob-Diffusion: A Global Consistent Diffusion Model for Large-Scale Image Generation

Kang, Yuhan, Shi, Hengcan, Liu, Hao, Xie, Weiying, Fang, Leyuan, Bruzzone, Lorenzo · 2026 · IEEE Transactions on Circuits and Systems for Video Technology

The DOI matches its Crossref record; 48 of the 48 references it cites were found in a registry or an index.

Abstract

Large-scale images play a crucial role in geospatial surveying, as they cover an extensively broad view and diverse objects. Due to computational limitations, existing methods rely on generating large-scale images in patches. However, the lack of global guidance in these methods often leads to significant logical errors among different patches. To address this issue, we propose a Global Consistency Diffusion model (Glob-Diffusion) for large-scale image generation. The core idea is to utilize the global consistency of small-scale images to guide the generation of large-scale images. Specifically, we introduce a Hierarchical Distributed Guidance (HDG) module that extracts patch prompts with different semantic hierarchies from small-scale images, distributedly embedding them into the generation of large-scale images to maintain global consistency across various regions. In addition, we further design a Region Guided Adapter (RGA) that dynamically optimizes the guidance strength of patch prompts by comparing differences across generated regions, effectively improving the realism of large-scale images. Our method demonstrates remarkable visual synthesis results across various natural scenes, effectively preserving global consistency in large-scale images, and also significantly enhancing the generation quality of large-scale remote sensing images. Code will be available at https://github.com/kyh433/Glob-Diffusion.

Overview

Integrity signals

Registry

Crossref · 10.1109/tcsvt.2025.3643743

Cites

48 of 48 references verified0 citation errors · 0 not checkable

Statistics

Recomputing p-values needs the paper’s full text.

Verification

Claims the paper makes

This paper’s full text isn’t openly available, so its claims and self-check weren’t run. The registry and citation checks still apply.

Citations

Cites

Show all 48 references

Research works printed but not linked: 14

  1. Bar-Tal, MultiDiffusion: Fusing diffusion paths for controlled image generation, 1737
  2. Li, BLIP: Bootstrapping language-image pre-training for unified vision-language understanding and generation, 12888
  3. Nichol, Improved denoising diffusion probabilistic models, 139, 8162
  4. Dhariwal, Diffusion models beat GANs on image synthesis, 34, 8780
  5. Lin, InfinityGAN: Towards infinite-pixel image synthesis
  6. Zhang, Towards coherent image inpainting using denoising diffusion implicit models, 41164
  7. Lee, SyncDiffusion: Coherent montage via synchronized joint diffusions, 50648
  8. Zhang, Continuous-multiple image outpainting in one-step via positional query and a diffusion-based approach
  9. He, ScaleCrafter: Tuning-free higher-resolution visual generation with diffusion models
  10. Song, Denoising diffusion implicit models
  11. Radford, Learning transferable visual models from natural language supervision, 8748
  12. Batifol, 2025, FLUX. 1 kontext: Flow matching for in-context image generation and editing in latent space
  13. Xie, SegFormer: Simple and efficient design for semantic segmentation with transformers, 12077
  14. Khanna, DiffusionSat: A generative foundation model for satellite imagery

Cited by

See all 2

Metadata

Authors
Kang, Y., Shi, H., Liu, H., Xie, W., Fang, L., & Bruzzone, L.
Affiliations
  • School of Artificial Intelligence and Robotics, Hunan University, Changsha, China
  • Hunan University (CN)
  • University of Trento (IT)
  • Xidian University (CN)
Venue
IEEE Transactions on Circuits and Systems for Video Technology
Published
2026-05
Volume
36
Issue
5
Pages
7005-7019
ISSN
  • 1051-8215 (ISSN-L)
  • 1558-2205
OpenAlex
W4417284342
Cited by
1
References
40
Citations by year
2026: 1
FWCI
0.35
Type
journal article
Language
en
Open access
closed
Locations
IEEE Transactions on Circuits and Systems for Video Technology (publishedVersion)
Funders
  • National Natural Science Foundation of China (62425109, U22B2014, 62221002, 62401202)
  • Science and Technology Plan Project Fund of Hunan Province (2022RC3064)
Topics
  • Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Generative Adversarial Networks and Image Synthesis
  • Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
  • Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Image Processing Techniques
Keywords
diffusion models, global consistency, semantic hierarchy

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: Glob-Diffusion: A Global Consistent Diffusion Model for Large-Scale Image Generation. https://app.cochat.ai/papers/10.1109/tcsvt.2025.3643743
The paper
Kang, Y., Shi, H., Liu, H., Xie, W., Fang, L., & Bruzzone, L. (2026). Glob-Diffusion: A Global Consistent Diffusion Model for Large-Scale Image Generation. IEEE Transactions on Circuits and Systems for Video Technology. https://doi.org/10.1109/tcsvt.2025.3643743

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.