mlsanityData to 14 Oct 2026

JPEG AIC2026: A large-scale dataset for fine-grained assessment of image coding

arXiv 2607.22783 ↗First posted 24 Jul 2026eess.IV cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

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. This paper introduces 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 eight conventional and four learning-based codecs across 17 coding configurations. Each source image is encoded using seven codecs. For each source-codec pair, decoded images are provided at 20 perceptually spaced distortion levels, corresponding approximately to 0.2-4.0 just-noticeable difference (JND) units using the ColorVideoVDP (CVVDP) metric 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. We report an extensive objective analysis using 24 conventional and 12 learning-based IQA methods. The results show substantial disagreement among current IQA methods for fine-grained quality differences, particularly for artifacts introduced by learning-based codecs. The complete dataset is publicly available at https://doi.org/10.18419/DARUS-6156.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 34 of its 79 references that are in the map. First posted on arXiv 24 Jul 2026.

Builds on

34 of 79 references.

References · 34

  1. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,177
  2. 2023DINOv2: Learning Robust Visual Features without Supervisioncited by 7,974
  3. 2020Image Quality Assessment: Unifying Structure and Texture Similaritycited by 811
  4. 2023DreamSim: Learning New Dimensions of Human Visual Similarity using Synthetic Datacited by 337
  5. 2023TOPIQ: A Top-down Approach from Semantics to Distortions for Image Quality Assessmentcited by 226
  6. 2016Deep Neural Networks for No-Reference and Full-Reference Image Quality Assessmentcited by 225
  7. 2018Generative Adversarial Networks for Extreme Learned Image Compressioncited by 219
  8. 2013Gradient Magnitude Similarity Deviation: A Highly Efficient Perceptual Image Quality Indexcited by 195
  9. 2018PieAPP: Perceptual Image-Error Assessment through Pairwise Preferencecited by 160
  10. 2019Image and Video Compression with Neural Networks: A Reviewcited by 86
  11. 2023Frequency-Aware Transformer for Learned Image Compressioncited by 58
  12. 2016A Haar Wavelet-Based Perceptual Similarity Index for Image Quality Assessmentcited by 57
22 more
  1. 2022Attentions Help CNNs See Better: Attention-based Hybrid Image Quality Assessment Networkcited by 57
  2. 2022COOL-CHIC: Coordinate-based Low Complexity Hierarchical Image Codeccited by 51
  3. 2022Shift-tolerant Perceptual Similarity Metriccited by 44
  4. 2023HDR-VDP-3: A multi-metric for predicting image differences, quality and contrast distortions in high dynamic range and regular contentcited by 41
  5. 2025Toward Generalized Image Quality Assessment: Relaxing the Perfect Reference Quality Assumptioncited by 35
  6. 2024ColorVideoVDP: A visual difference predictor for image, video and display distortionscited by 34
  7. 20242AFC Prompting of Large Multimodal Models for Image Quality Assessmentcited by 20
  8. 2024Good, Cheap, and Fast: Overfitted Image Compression with Wasserstein Distortioncited by 13
  9. 2022DeepDC: Deep Distance Correlation as a Perceptual Image Quality Evaluatorcited by 11
  10. 2021Subjective Image Quality Assessment with Boosted Triplet Comparisonscited by 9
  11. 2023Wasserstein Distortion: Unifying Fidelity and Realismcited by 8
  12. 2025An Overview of the JPEG AI Learning-Based Image Coding Standardcited by 6
  13. 2022Perceptual Quality Assessment for Fine-Grained Compressed Imagescited by 5
  14. 2021Versatile Video Coding Standard: A Review from Coding Tools to Consumers Deploymentcited by 4
  15. 2025Subjective Visual Quality Assessment for High-Fidelity Learning-Based Image Compressioncited by 3
  16. 2026Cool-chic 5.0: Faster Encoding and Inter-Feature Entropy Modeling for Overfitted Image Compressioncited by 3
  17. 2024Users prefer Jpegli over same-sized libjpeg-turbo or MozJPEGcited by 2
  18. 2025Evaluating quality metrics through the lenses of psychophysical measurements of low-level visioncited by 2
  19. 2025Overview of Variable Rate Coding in JPEG AIcited by 2
  20. 2025The JPEG XL Image Coding System: History, Features, Coding Tools, Design Rationale, and Futurecited by 2
  21. 2025Fine-Grained HDR Image Quality Assessment From Noticeably Distorted to Very High Fidelitycited by 1
  22. 2025Evaluation of Objective Image Quality Metrics for High-Fidelity Image Compressioncited by 1

Built on by

Not cited yet.