mlsanityData to 14 Oct 2026

Exploring the Naturalness of AI-Generated Images

arXiv 2312.05476 ↗First posted 9 Dec 2023cs.CVcited by 22

Not on the map. Why?

Abstract (arXiv)

The proliferation of Artificial Intelligence-Generated Images (AGIs) has greatly expanded the Image Naturalness Assessment (INA) problem. Different from early definitions that mainly focus on tone-mapped images with limited distortions (e.g., exposure, contrast, and color reproduction), INA on AI-generated images is especially challenging as it has more diverse contents and could be affected by factors from multiple perspectives, including low-level technical distortions and high-level rationality distortions. In this paper, we take the first step to benchmark and assess the visual naturalness of AI-generated images. First, we construct the AI-Generated Image Naturalness (AGIN) database by conducting a large-scale subjective study to collect human opinions on the overall naturalness as well as perceptions from technical and rationality perspectives. AGIN verifies that naturalness is universally and disparately affected by technical and rationality distortions. Second, we propose the Joint Objective Image Naturalness evaluaTor (JOINT), to automatically predict the naturalness of AGIs that aligns human ratings. Specifically, JOINT imitates human reasoning in naturalness evaluation by jointly learning both technical and rationality features. We demonstrate that JOINT significantly outperforms baselines for providing more subjectively consistent results on naturalness assessment.

Key facts. Cited by 22 papers in the map (data through 14 Oct 2026). Builds on 66 of its 126 references that are in the map. First posted on arXiv 9 Dec 2023.

Builds on

66 of 126 references.

References · 66

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  3. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  4. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  5. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,139
  6. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,177
  7. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,498
  8. 2022Hierarchical Text-Conditional Image Generation with CLIP Latentscited by 6,585
  9. 2022Photorealistic Text-to-Image Diffusion Models with Deep Language Understandingcited by 6,355
  10. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 6,013
  11. 2023Adding Conditional Control to Text-to-Image Diffusion Modelscited by 5,503
  12. 2014Deep Learning Face Attributes in the Wildcited by 3,693
38 more
  1. 2021GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Modelscited by 3,614
  2. 2019Analyzing and Improving the Image Quality of StyleGANcited by 3,588
  3. 2016Improved Techniques for Training GANscited by 2,970
  4. 2022InstructPix2Pix: Learning to Follow Image Editing Instructionscited by 2,611
  5. 2021CLIPScore: A Reference-free Evaluation Metric for Image Captioningcited by 2,424
  6. 2022RePaint: Inpainting using Denoising Diffusion Probabilistic Modelscited by 1,430
  7. 2018Demystifying MMD GANscited by 1,293
  8. 2021MUSIQ: Multi-scale Image Quality Transformercited by 1,081
  9. 2021StyleCLIP: Text-Driven Manipulation of StyleGAN Imagerycited by 991
  10. 2022Exploring CLIP for Assessing the Look and Feel of Imagescited by 991
  11. 2023Pick-a-Pic: An Open Dataset of User Preferences for Text-to-Image Generationcited by 977
  12. 2019Improved Precision and Recall Metric for Assessing Generative Modelscited by 944
  13. 2023MagicBrush: A Manually Annotated Dataset for Instruction-Guided Image Editingcited by 624
  14. 2022MANIQA: Multi-dimension Attention Network for No-Reference Image Quality Assessmentcited by 522
  15. 2019KonIQ-10k: An ecologically valid database for deep learning of blind image quality assessmentcited by 355
  16. 2023GenImage: A Million-Scale Benchmark for Detecting AI-Generated Imagecited by 321
  17. 2022Exploring Video Quality Assessment on User Generated Contents from Aesthetic and Technical Perspectivescited by 320
  18. 2019Blind Image Quality Assessment Using A Deep Bilinear Convolutional Neural Networkcited by 302
  19. 2023InternLM-XComposer: A Vision-Language Large Model for Advanced Text-image Comprehension and Compositioncited by 297
  20. 2023Blind Image Quality Assessment via Vision-Language Correspondence: A Multitask Learning Perspectivecited by 280
  21. 2023A Comprehensive Survey of AI-Generated Content (AIGC): A History of Generative AI from GAN to ChatGPTcited by 224
  22. 2019From Patches to Pictures (PaQ-2-PiQ): Mapping the Perceptual Space of Picture Qualitycited by 223
  23. 2023Drag Your GAN: Interactive Point-based Manipulation on the Generative Image Manifoldcited by 219
  24. 2022MAT: Mask-Aware Transformer for Large Hole Image Inpaintingcited by 218
  25. 2015Massive Online Crowdsourced Study of Subjective and Objective Picture Qualitycited by 209
  26. 2020Fast Differentiable Sorting and Rankingcited by 197
  27. 2022FAST-VQA: Efficient End-to-end Video Quality Assessment with Fragment Samplingcited by 179
  28. 2020PIPAL: a Large-Scale Image Quality Assessment Dataset for Perceptual Image Restorationcited by 178
  29. 2018PieAPP: Perceptual Image-Error Assessment through Pairwise Preferencecited by 160
  30. 2023Q-Instruct: Improving Low-level Visual Abilities for Multi-modality Foundation Modelscited by 152
  31. 2022Diffusion-based Image Translation using Disentangled Style and Content Representationcited by 149
  32. 2023AGIQA-3K: An Open Database for AI-Generated Image Quality Assessmentcited by 142
  33. 2020Uncertainty-Aware Blind Image Quality Assessment in the Laboratory and Wildcited by 134
  34. 2020Cross-domain Correspondence Learning for Exemplar-based Image Translationcited by 116
  35. 2021Blindly Assess Quality of In-the-Wild Videos via Quality-aware Pre-training and Motion Perceptioncited by 97
  36. 2021Blind Quality Assessment for in-the-Wild Images via Hierarchical Feature Fusion and Iterative Mixed Database Trainingcited by 71
  37. 2023Toward Verifiable and Reproducible Human Evaluation for Text-to-Image Generationcited by 68
  38. 2023AIGCIQA2023: A Large-scale Image Quality Assessment Database for AI Generated Images: from the Perspectives of Quality, Authenticity and Correspondencecited by 61

50 most cited of 66 All 66 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 10; 2025: 6; 2026: 6.

22 papers.

Sort:

By area:

  1. 2024A-Bench: Are LMMs Masters at Evaluating AI-generated Images?cited by 39
  2. 2024FakeBench: Probing Explainable Fake Image Detection via Large Multimodal Modelscited by 36
  3. 2024AIGIQA-20K: A Large Database for AI-Generated Image Quality Assessmentcited by 33
  4. 2024GAIA: Rethinking Action Quality Assessment for AI-Generated Videoscited by 30
  5. 2024Quality Assessment in the Era of Large Models: A Surveycited by 26
  6. 2024NTIRE 2024 Quality Assessment of AI-Generated Content Challengecited by 20
  7. 2024Video Quality Assessment: A Comprehensive Surveycited by 15
  8. 2025Next Token Is Enough: Realistic Image Quality and Aesthetic Scoring with Multimodal Large Language Modelcited by 12
  9. 2024G-Refine: A General Quality Refiner for Text-to-Image Generationcited by 8
  10. 2024AI-generated Image Quality Assessment in Visual Communicationcited by 7
  11. 2025Evaluating and Predicting Distorted Human Body Parts for Generated Imagescited by 5
  12. 2025Q-Save: Towards Scoring and Attribution for Generated Video Evaluationcited by 4
10 more
  1. 2024Quality Prediction of AI Generated Images and Videos: Emerging Trends and Opportunitiescited by 3
  2. 2025GeneVA: A Dataset of Human Annotations for Generative Text to Video Artifactscited by 2
  3. 2025Lacking Data? No worries! How synthetic images can alleviate image scarcity in wildlife surveys: a case study with muskox (Ovibos moschatus)cited by 2
  4. 2025RAISE: Realness Assessment for Image Synthesis and Evaluationcited by 1
  5. 2026ELIQ: A Label-Free Framework for Quality Assessment of Evolving AI-Generated Imagescited by 1
  6. 2026Bi-Level Prompt Optimization for Multimodal LLM-as-a-Judgecited by 1
  7. 2026Multi-Task Reinforcement Learning for Enhanced Multimodal LLM-as-a-Judgecited by 0
  8. 2026TASTE: A Designer-Annotated Multi-Dimensional Preference Dataset for AI-Generated Graphic Designcited by 0
  9. 2026CV-Arena: An Open Benchmark for Instructional Computer Vision Problem Solving with Human-AI Collaborative Preferencescited by 0
  10. 2026Evaluating the Evaluators: Diagnosing Large Multimodal Models for AI-Generated Image Assessmentcited by 0