CoChat

No-reference image quality assessment based on global awareness

Open access
Hu, Zhigang, Yang, Gege, Du, Zhe, Huang, Xiaodong, Zhang, Pujing, Liu, Dechun · 2024 · PLOS ONE

The DOI matches its Crossref record; 54 of the 54 references it cites were found in a registry or an index.

Abstract

In the field of computer vision, the application of hand-crafted as well as computer-learning-based methods in the field of image quality assessment has yielded remarkable results. However, in the field of no-reference image distortion, it is still challenging to accurately perceive and determine the quality of an image. To address the difficulties of Image Quality Assessment (IQA) in the field of authentic distorted images, we consider the use of the Swin Transformer (ST) to extract features. To enable the model to focus on both spatial and channel information of features, we design a plug-and-play Global Self-Attention Block (GSAB). At the same time, we introduce a Transformer block in the model to enhance the model’s ability to capture long-range dependencies. Finally, we derive the prediction of image quality scores through a Dual-Branching structure. Our method is experimented on four synthetic datasets as well as two authentic datasets, and the results of the experiments are weighted according to the size of the datasets, and the results show that our method outperforms all the current methods and works well in the Generalization ability test, which proves that our method has a good generalization ability. The code will be posted subsequently at https://github.com/yanggege-new/NR-IQA-based-on-global-awareness.

Overview

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1371/journal.pone.0310206

Cites

54 of 54 references verified0 citation errors · 0 not checkable

Statistics

Figures

Fig 1 No-reference image quality assessment based on ST. The distorted image is fed into the Swin Transformer (Fig 2) for feature extraction. ‘Global Self-Attention Block’ details the information interaction between the global self-attention block space and the channel dimensions. ‘Quality prediction block with dual-branching structure’ details how the two-branch structure can be used for quality prediction.
Fig 1 No-reference image quality assessment based on ST. The distorted image is fed into the Swin Transformer (Fig 2) for feature extraction. ‘Global Self-Attention Block’ details the information interaction between the global self-attention block space and the channel dimensions. ‘Quality prediction block with dual-branching structure’ details how the two-branch structure can be used for quality prediction.CC BY · PubMed Central
Fig 2 Left: Transformer Block, right: Swin Transformer Block. W-MSA is multi-head self-attention modules with regular configuration and SW-MSA is multi-head self-attention modules with shifted windowing configuration. LN is Layernorm.
Fig 2 Left: Transformer Block, right: Swin Transformer Block. W-MSA is multi-head self-attention modules with regular configuration and SW-MSA is multi-head self-attention modules with shifted windowing configuration. LN is Layernorm.CC BY · PubMed Central
Fig 3 Global self-attention block.
Fig 3 Global self-attention block.CC BY · PubMed Central
Fig 4 Example image from CSIQ [11] dataset. On the left is the original image on the right is the distorted image, below are the image manual evaluation scores DMOS and our model predicted scores respectively, it can be observed that our model has high accuracy.
Fig 4 Example image from CSIQ [11] dataset. On the left is the original image on the right is the distorted image, below are the image manual evaluation scores DMOS and our model predicted scores respectively, it can be observed that our model has high accuracy.CC BY · PubMed Central
Fig 5 Scatterplot of the CSIQ dataset and regression curves with predicted scores in the horizontal coordinate and DMOS values subjectively observed by the human eye in the vertical coordinate.
Fig 5 Scatterplot of the CSIQ dataset and regression curves with predicted scores in the horizontal coordinate and DMOS values subjectively observed by the human eye in the vertical coordinate.CC BY · PubMed Central
Fig 6 Scatterplot of the KonIQ-10k dataset and regression curves with predicted scores in the horizontal coordinate and MOS values subjectively observed by the human eye in the vertical coordinate.
Fig 6 Scatterplot of the KonIQ-10k dataset and regression curves with predicted scores in the horizontal coordinate and MOS values subjectively observed by the human eye in the vertical coordinate.CC BY · PubMed Central
Fig 7 Ablation results on CSIQ and KADID.
Fig 7 Ablation results on CSIQ and KADID.CC BY · PubMed Central
Fig 8 Visualization of patch score maps, patch weight maps and final weighted maps of the dataset of the CSIQ [11].
Fig 8 Visualization of patch score maps, patch weight maps and final weighted maps of the dataset of the CSIQ [11].CC BY · PubMed Central

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

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?

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

1 retracted

Show all 54 references

Research works printed but not linked: 8

  1. T-Y Chiu, 2020, editors. Assessing image quality issues for real-world problems., proceedings of the IEEE/CVF conference on computer vision and pattern recognition, 3646
  2. S Yang, 2022, editors. Maniqa: Multi-dimension attention network for no-reference image quality assessment, Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 1191
  3. T. Chandra Mohan, 2021, Blind Image Quality Assessment of Smartphone-captured Images in the Wild: University of Twente
  4. IEEE, 2012, editors. Unsupervised feature learning framework for no-reference image quality assessment., 2012 IEEE conference on computer vision and pattern recognition;
  5. P Ye, 2014, editors. Beyond human opinion scores: Blind image quality assessment based on synthetic scores, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 4241
  6. H Zhu, 2020, editors. MetaIQA: Deep meta-learning for no-reference image quality assessment, Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, 14143
  7. D Liu, 2017, editors. Robust video super-resolution with learned temporal dynamics, Proceedings of the IEEE International Conference on Computer Vision, 2507
  8. IEEE, 2021, editors. Transformer for image quality assessment., 2021 IEEE International Conference on Image Processing (ICIP);

Cited by

See all 9

Metadata

Authors
Hu, Z., Yang, G., Du, Z., Huang, X., Zhang, P., & Liu, D.
Affiliations
  • Henan University of Science and Technology (CN)
  • First Affiliated Hospital of Henan University of Science and Technology (CN)
Corresponding author
Liu, Dechun
Venue
PLOS ONE
Published
2024-10-07
Volume
19
Issue
10
Pages
e0310206
ISSN
1932-6203 (ISSN-L)
OpenAlex
W4403183724
Cited by
5
References
52
Citations by year
2026: 2 · 2025: 3
FWCI
0.70
Type
journal article
Language
en
Open access
Locations
  • PLoS ONE (publishedVersion, cc-by)
  • PubMed Central (publishedVersion, cc-by)
  • PubMed (publishedVersion)
  • RePEc: Research Papers in Economics (submittedVersion)
  • DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion)
Funders
Henan Province Medical Science and Technology Tackle Key Problems Project (LHGJ20230459)
Topics
  • Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Image and Video Quality Assessment
  • Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Digital Media Forensic Detection
  • Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Image Retrieval and Classification Techniques
Keywords
no-reference image quality assessment, image distortion, Swin Transformer, global self-attention, long-range dependencies, dual-branch network, model generalization
MeSH terms
Algorithms, Humans, Image Processing, Computer-Assisted

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: No-reference image quality assessment based on global awareness. https://app.cochat.ai/papers/10.1371/journal.pone.0310206
The paper
Hu, Z., Yang, G., Du, Z., Huang, X., Zhang, P., & Liu, D. (2024). No-reference image quality assessment based on global awareness. PLOS ONE. https://doi.org/10.1371/journal.pone.0310206

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.