|
Persistent Identifier
|
doi:10.18419/DARUS-6156 |
|
Publication Date
|
2026-07-01 |
|
Title
| JPEG AIC2026: Fine-grained image compression dataset |
|
Author
| Jenadeleh, Mohsenhttps://ror.org/0546hnb39ORCIDhttps://orcid.org/0000-0002-8216-1195
Sneyers, JonCloudinaryORCIDhttps://orcid.org/0009-0008-1697-2855
Ascenso, Joãohttps://ror.org/02ht4fk33ORCIDhttps://orcid.org/0000-0001-9902-5926 |
|
Point of Contact
|
Use email button above to contact.
Jenadeleh, Mohsen (University of Konstanz)
Sneyers, Jon (Cloudinary) |
|
Description
| Recent advances in conventional and learning-based image coding have increased the demand for benchmark datasets that support fine-grained assessment of compressed image quality, particularly for learning-based image compression methods.
The data in this dataset represent Assessment of Image Coding 2026 (AIC2026), a large-scale dataset for high-fidelity image compression containing 70 source images selected from 2,787 candidates using semantic clustering, inter-metric disagreement among objective image quality assessment (IQA) methods, and manual inspection and refinement. The dataset covers a wide range of compression artifacts produced by 8 conventional and 4 learning-based codecs across 17 coding configurations. Each source image is encoded using 7 codecs. For each source-codec pair, decoded images are provided at 20 perceptually spaced distortion levels, corresponding approximately to 0.2-4.0 JND using CVVDP for distortion estimation, yielding 9,618 distorted images. This fine-grained sampling enables analysis of rate-distortion behavior and objective metric evaluation for subtle quality differences across a wide range of compression artifacts.
An extensive objective analysis using 24 conventional and 12 learning-based IQA methods shows substantial disagreement among current IQA methods for fine-grained quality differences, particularly for artifacts introduced by learning-based codecs.
More information about the dataset including dataset structure, file naming conventions, codec acronyms, accompanying metadata files, citation information, and licensing terms. can be found in the README. (2026-06-30) |
|
Subject
| Computer and Information Science |
|
Keyword
| Image Dataset http://www.wikidata.org/entity/Q124305192 (Wikidata)
Image Compression https://www.wikidata.org/entity/Q412438 (Wikidata)
Compression Artifact https://www.wikidata.org/entity/Q1097775 (Wikidata)
Just-Noticeable Difference https://www.wikidata.org/entity/Q1224386 (Wikidata)
Image Quality https://www.wikidata.org/entity/Q3813865 (Wikidata)
Objective Quality Metric https://www.wikidata.org/entity/Q44285546 (Wikidata) |
|
Topic Classification
| Image and Language Processing, Computer Graphics and Visualisation, Human Computer Interaction, Ubiquitous and Wearable Computing (DFGFO) https://w3id.org/dfgfo/2024/443-05 |
|
Related Publication
| Is Cited By: Jenadeleh, M., Sneyers, J., Ascenso, J., Richter, T., Karabutov, A., Jia, P., Alshina, E., Watanabe, O., Pinheiro, A., Ebrahimi, T. and Saupe, D. (2026) JPEG AIC2026: A Large-Scale Dataset for Fine-Grained Assessment of Image Coding. arXiv [Preprint]. doi arXiv.2607.22783 https://doi.org/10.48550/arXiv.2607.22783 |
|
Producer
| Jenadeleh, Mohsen (University of Konstanz) https://orcid.org/0000-0002-8216-1195 
Sneyers, Jon (Cloudinary) https://orcid.org/0009-0008-1697-2855 
|
|
Project
| Fine-grained visual quality assessment and modeling for high-fidelity compressed images |
|
Funding Information
| DFG: Fine-grained visual quality assessment and modeling for high-fidelity compressed images: 496858717
DFG: SFB/Transregio 161: 251654672 |
|
Depositor
| Jenadeleh, Mohsen |
|
Deposit Date
| 2026-06-13 |
