mlsanityData to 14 Oct 2026

AGIQA-3K: An Open Database for AI-Generated Image Quality Assessment

arXiv 2306.04717 ↗First posted 7 Jun 2023cs.CV cs.AI eess.IVcited by 142

Not on the map. Why?

Cited by 27 in Multimodal LLMs / vision-language models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

With the rapid advancements of the text-to-image generative model, AI-generated images (AGIs) have been widely applied to entertainment, education, social media, etc. However, considering the large quality variance among different AGIs, there is an urgent need for quality models that are consistent with human subjective ratings. To address this issue, we extensively consider various popular AGI models, generated AGI through different prompts and model parameters, and collected subjective scores at the perceptual quality and text-to-image alignment, thus building the most comprehensive AGI subjective quality database AGIQA-3K so far. Furthermore, we conduct a benchmark experiment on this database to evaluate the consistency between the current Image Quality Assessment (IQA) model and human perception, while proposing StairReward that significantly improves the assessment performance of subjective text-to-image alignment. We believe that the fine-grained subjective scores in AGIQA-3K will inspire subsequent AGI quality models to fit human subjective perception mechanisms at both perception and alignment levels and to optimize the generation result of future AGI models. The database is released on https://github.com/lcysyzxdxc/AGIQA-3k-Database.

Key facts. Cited by 142 papers in the map (data through 14 Oct 2026). Builds on 44 of its 77 references that are in the map. First posted on arXiv 7 Jun 2023.

Builds on

44 of 77 references.

References · 44

  1. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  2. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  3. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  4. 2022Hierarchical Text-Conditional Image Generation with CLIP Latentscited by 6,585
  5. 2021Zero-Shot Text-to-Image Generationcited by 4,288
  6. 2021GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Modelscited by 3,614
  7. 2016Improved Techniques for Training GANscited by 2,970
  8. 2021CLIPScore: A Reference-free Evaluation Metric for Image Captioningcited by 2,424
  9. 2022Scaling Autoregressive Models for Content-Rich Text-to-Image Generationcited by 1,295
  10. 2018Demystifying MMD GANscited by 1,293
  11. 2023ImageReward: Learning and Evaluating Human Preferences for Text-to-Image Generationcited by 1,045
  12. 2022Exploring CLIP for Assessing the Look and Feel of Imagescited by 991
32 more
  1. 2023Pick-a-Pic: An Open Dataset of User Preferences for Text-to-Image Generationcited by 977
  2. 2016Generative Adversarial Text to Image Synthesiscited by 735
  3. 2021CogView: Mastering Text-to-Image Generation via Transformerscited by 694
  4. 2017AttnGAN: Fine-Grained Text to Image Generation with Attentional Generative Adversarial Networkscited by 664
  5. 2016StackGAN: Text to Photo-realistic Image Synthesis with Stacked Generative Adversarial Networkscited by 577
  6. 2017NIMA: Neural Image Assessmentcited by 389
  7. 2022DiffusionDB: A Large-scale Prompt Gallery Dataset for Text-to-Image Generative Modelscited by 379
  8. 2019KonIQ-10k: An ecologically valid database for deep learning of blind image quality assessmentcited by 355
  9. 2019Blind Image Quality Assessment Using A Deep Bilinear Convolutional Neural Networkcited by 302
  10. 2023Human Preference Score: Better Aligning Text-to-Image Models with Human Preferencecited by 287
  11. 2023Blind Image Quality Assessment via Vision-Language Correspondence: A Multitask Learning Perspectivecited by 280
  12. 2023Text-to-image Diffusion Models in Generative AI: A Surveycited by 265
  13. 2020The Creation and Detection of Deepfakes: A Surveycited by 247
  14. 2019From Patches to Pictures (PaQ-2-PiQ): Mapping the Perceptual Space of Picture Qualitycited by 223
  15. 2021No-Reference Image Quality Assessment via Transformers, Relative Ranking, and Self-Consistencycited by 166
  16. 2020Uncertainty-Aware Blind Image Quality Assessment in the Laboratory and Wildcited by 134
  17. 2022CLIP-ViP: Adapting Pre-trained Image-Text Model to Video-Language Representation Alignmentcited by 74
  18. 2021Blind Quality Assessment for in-the-Wild Images via Hierarchical Feature Fusion and Iterative Mixed Database Trainingcited by 71
  19. 2023Seeing is not always believing: Benchmarking Human and Model Perception of AI-Generated Imagescited by 66
  20. 2022Text-Guided Synthesis of Artistic Images with Retrieval-Augmented Diffusion Modelscited by 64
  21. 2022Generated Faces in the Wild: Quantitative Comparison of Stable Diffusion, Midjourney and DALL-E 2cited by 55
  22. 2023A Perceptual Quality Assessment Exploration for AIGC Imagescited by 55
  23. 2021Adversarial Text-to-Image Synthesis: A Reviewcited by 52
  24. 2023A Pathway Towards Responsible AI Generated Contentcited by 38
  25. 2023X-IQE: eXplainable Image Quality Evaluation for Text-to-Image Generation with Visual Large Language Modelscited by 28
  26. 2022Prompt-based Learning for Unpaired Image Captioningcited by 23
  27. 2023VDPVE: VQA Dataset for Perceptual Video Enhancementcited by 22
  28. 2019No-Reference Quality Assessment of Contrast-Distorted Images using Contrast Enhancementcited by 14
  29. 2023Light-VQA: A Multi-Dimensional Quality Assessment Model for Low-Light Video Enhancementcited by 12
  30. 2017Assessing Visual Quality of Omnidirectional Videoscited by 11
  31. 2023Learning to Evaluate the Artness of AI-generated Imagescited by 10
  32. 2023A real-time blind quality-of-experience assessment metric for HTTP adaptive streamingcited by 5

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 13; 2024: 59; 2025: 42; 2026: 28.

142 papers.

Sort:

By area:

  1. 2023Human Preference Score v2: A Solid Benchmark for Evaluating Human Preferences of Text-to-Image Synthesiscited by 890
  2. 2023Q-Bench: A Benchmark for General-Purpose Foundation Models on Low-level Visioncited by 249
  3. 2023TOPIQ: A Top-down Approach from Semantics to Distortions for Image Quality Assessmentcited by 226
  4. 2024VisionReward: Fine-Grained Multi-Dimensional Human Preference Learning for Image and Video Generationcited by 156
  5. 2023Q-Instruct: Improving Low-level Visual Abilities for Multi-modality Foundation Modelscited by 152
  6. 2025Teaching Large Language Models to Regress Accurate Image Quality Scores using Score Distributioncited by 141
  7. 2024Learning Multi-dimensional Human Preference for Text-to-Image Generationcited by 106
  8. 2025Q-Insight: Understanding Image Quality via Visual Reinforcement Learningcited by 98
  9. 2023InstructVideo: Instructing Video Diffusion Models with Human Feedbackcited by 86
  10. 2024Towards Open-ended Visual Quality Comparisoncited by 85
  11. 2025VisualQuality-R1: Reasoning-Induced Image Quality Assessment via Reinforcement Learning to Rankcited by 79
  12. 2024Adaptive Image Quality Assessment via Teaching Large Multimodal Model to Comparecited by 66
38 more
  1. 2024AesBench: An Expert Benchmark for Multimodal Large Language Models on Image Aesthetics Perceptioncited by 65
  2. 2024LiFT: Leveraging Human Feedback for Text-to-Video Model Alignmentcited by 53
  3. 2024A Comprehensive Study of Multimodal Large Language Models for Image Quality Assessmentcited by 43
  4. 2024A-Bench: Are LMMs Masters at Evaluating AI-generated Images?cited by 39
  5. 2024FakeBench: Probing Explainable Fake Image Detection via Large Multimodal Modelscited by 36
  6. 2024AIGIQA-20K: A Large Database for AI-Generated Image Quality Assessmentcited by 33
  7. 2024Quality-Aware Image-Text Alignment for Opinion-Unaware Image Quality Assessmentcited by 32
  8. 2023Enhancing Diffusion Models with Text-Encoder Reinforcement Learningcited by 30
  9. 2024R-Bench: Are your Large Multimodal Model Robust to Real-world Corruptions?cited by 30
  10. 2023Advancing Zero-Shot Digital Human Quality Assessment through Text-Prompted Evaluationcited by 27
  11. 2024AIGV-Assessor: Benchmarking and Evaluating the Perceptual Quality of Text-to-Video Generation with LMMcited by 24
  12. 2023Measuring the Quality of Text-to-Video Model Outputs: Metrics and Datasetcited by 23
  13. 2023Exploring the Naturalness of AI-Generated Imagescited by 22
  14. 2024Q-Refine: A Perceptual Quality Refiner for AI-Generated Imagecited by 21
  15. 2024NTIRE 2024 Quality Assessment of AI-Generated Content Challengecited by 20
  16. 2025HumanAesExpert: Advancing a Multi-Modality Foundation Model for Human Image Aesthetic Assessmentcited by 19
  17. 2024AIGCOIQA2024: Perceptual Quality Assessment of AI Generated Omnidirectional Imagescited by 16
  18. 2023StableVQA: A Deep No-Reference Quality Assessment Model for Video Stabilitycited by 15
  19. 2024SynArtifact: Classifying and Alleviating Artifacts in Synthetic Images via Vision-Language Modelcited by 15
  20. 2024Video Quality Assessment: A Comprehensive Surveycited by 15
  21. 2023PKU-I2IQA: An Image-to-Image Quality Assessment Database for AI Generated Imagescited by 14
  22. 2024PromptIQA: Boosting the Performance and Generalization for No-Reference Image Quality Assessment via Promptscited by 14
  23. 2024CLIP-AGIQA: Boosting the Performance of AI-Generated Image Quality Assessment with CLIPcited by 14
  24. 2024VisualCritic: Making LMMs Perceive Visual Quality Like Humanscited by 13
  25. 2024Quality Assessment for AI Generated Images with Instruction Tuningcited by 13
  26. 2024UniQA: Unified Vision-Language Pre-training for Image Quality and Aesthetic Assessmentcited by 13
  27. 2024HEIE: MLLM-Based Hierarchical Explainable AIGC Image Implausibility Evaluatorcited by 13
  28. 2025Q-SiT: Teaching LMMs for Image Quality Scoring and Interpretingcited by 13
  29. 2025AGHI-QA: A Subjective-Aligned Dataset and Metric for AI-Generated Human Imagescited by 13
  30. 2024Bringing Textual Prompt to AI-Generated Image Quality Assessmentcited by 12
  31. 2024Is this Generated Person Existed in Real-world? Fine-grained Detecting and Calibrating Abnormal Human-bodycited by 12
  32. 2024Grounding-IQA: Grounding Multimodal Language Model for Image Quality Assessmentcited by 12
  33. 2025Image Quality Assessment: From Human to Machine Preferencecited by 12
  34. 2024Opinion-Unaware Blind Image Quality Assessment using Multi-Scale Deep Feature Statisticscited by 11
  35. 2023PSCR: Patches Sampling-based Contrastive Regression for AIGC Image Quality Assessmentcited by 10
  36. 2024Adaptive Mixed-Scale Feature Fusion Network for Blind AI-Generated Image Quality Assessmentcited by 10
  37. 2024F-Bench: Rethinking Human Preference Evaluation Metrics for Benchmarking Face Generation, Customization, and Restorationcited by 10
  38. 2025Self-Evolving Vision-Language Models for Image Quality Assessment via Voting and Rankingcited by 10

50 most cited of 142 All 142 (JSON)