mlsanityData to 7 Oct 2026

Shadows Don't Lie and Lines Can't Bend! Generative Models don't know Projective Geometry...for now

arXiv 2311.17138 ↗First posted 28 Nov 2023cs.CV cs.AI cs.GRcited by 61

Not on the map. Why?

Abstract (arXiv)

Generative models can produce impressively realistic images. This paper demonstrates that generated images have geometric features different from those of real images. We build a set of collections of generated images, prequalified to fool simple, signal-based classifiers into believing they are real. We then show that prequalified generated images can be identified reliably by classifiers that only look at geometric properties. We use three such classifiers. All three classifiers are denied access to image pixels, and look only at derived geometric features. The first classifier looks at the perspective field of the image, the second looks at lines detected in the image, and the third looks at relations between detected objects and shadows. Our procedure detects generated images more reliably than SOTA local signal based detectors, for images from a number of distinct generators. Saliency maps suggest that the classifiers can identify geometric problems reliably. We conclude that current generators cannot reliably reproduce geometric properties of real images.

Key facts. Cited by 61 papers in the map (data through 7 Oct 2026). Builds on 34 of its 50 references that are in the map. First posted on arXiv 28 Nov 2023.

Builds on

34 of 50 references.

References · 34

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  3. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  4. 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,690
  5. 2022Hierarchical Text-Conditional Image Generation with CLIP Latentscited by 6,539
  6. 2022Photorealistic Text-to-Image Diffusion Models with Deep Language Understandingcited by 6,322
  7. 2023BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Modelscited by 6,069
  8. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 5,986
  9. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,223
  10. 2022BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generationcited by 4,310
  11. 2023SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesiscited by 4,290
  12. 2019Analyzing and Improving the Image Quality of StyleGANcited by 3,580
22 more
  1. 2016Improved Techniques for Training GANscited by 2,938
  2. 2021CLIPScore: A Reference-free Evaluation Metric for Image Captioningcited by 2,388
  3. 2015LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loopcited by 1,350
  4. 2018BDD100K: A Diverse Driving Dataset for Heterogeneous Multitask Learningcited by 1,282
  5. 2021Alias-Free Generative Adversarial Networkscited by 1,181
  6. 2023PixArt-α: Fast Training of Diffusion Transformer for Photorealistic Text-to-Image Synthesiscited by 854
  7. 2019CNN-generated images are surprisingly easy to spot... for nowcited by 842
  8. 2023DIRE for Diffusion-Generated Image Detectioncited by 386
  9. 2020What makes fake images detectable? Understanding properties that generalizecited by 272
  10. 2023Holistic Evaluation of Text-To-Image Modelscited by 160
  11. 2023Davidsonian Scene Graph: Improving Reliability in Fine-grained Evaluation for Text-to-Image Generationcited by 159
  12. 2018Learning Rich Features for Image Manipulation Detectioncited by 154
  13. 2018Fighting Fake News: Image Splice Detection via Learned Self-Consistencycited by 136
  14. 2022Perspective Fields for Single Image Camera Calibrationcited by 75
  15. 2023ImagenHub: Standardizing the evaluation of conditional image generation modelscited by 75
  16. 2023OBJECT 3DIT: Language-guided 3D-aware Image Editingcited by 62
  17. 2022DeepLSD: Line Segment Detection and Refinement with Deep Image Gradientscited by 58
  18. 2019Detecting Photoshopped Faces by Scripting Photoshopcited by 55
  19. 2023Online Detection of AI-Generated Imagescited by 55
  20. 2023StyleGAN knows Normal, Depth, Albedo, and Morecited by 44
  21. 2023Beyond Surface Statistics: Scene Representations in a Latent Diffusion Modelcited by 29
  22. 2022Instance Shadow Detection with A Single-Stage Detectorcited by 22

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 1; 2024: 24; 2025: 19; 2026: 17.

61 papers.

Sort:

By area:

  1. 2024CAT3D: Create Anything in 3D with Multi-View Diffusion Modelscited by 425
  2. 2023VIEScore: Towards Explainable Metrics for Conditional Image Synthesis Evaluationcited by 196
  3. 2024Probing the 3D Awareness of Visual Foundation Modelscited by 175
  4. 2024Any-Resolution AI-Generated Image Detection by Spectral Learningcited by 56
  5. 2024Zero-Shot Detection of AI-Generated Imagescited by 50
  6. 2024A Single Simple Patch is All You Need for AI-generated Image Detectioncited by 43
  7. 2024Fake or JPEG? Revealing Common Biases in Generated Image Detection Datasetscited by 43
  8. 2024LumiNet: Latent Intrinsics Meets Diffusion Models for Indoor Scene Relightingcited by 37
  9. 2024FakeBench: Probing Explainable Fake Image Detection via Large Multimodal Modelscited by 36
  10. 2025AIGI-Holmes: Towards Explainable and Generalizable AI-Generated Image Detection via Multimodal Large Language Modelscited by 33
  11. 2024Videoshop: Localized Semantic Video Editing with Noise-Extrapolated Diffusion Inversioncited by 27
  12. 2024Photorealistic Object Insertion with Diffusion-Guided Inverse Renderingcited by 27
38 more
  1. 2025Bridging the Gap Between Ideal and Real-world Evaluation: Benchmarking AI-Generated Image Detection in Challenging Scenarioscited by 24
  2. 2024Collaborative Control for Geometry-Conditioned PBR Image Generationcited by 22
  3. 2025Epipolar Geometry Improves Video Generation Modelscited by 22
  4. 2024VersaT2I: Improving Text-to-Image Models with Versatile Rewardcited by 17
  5. 2024Reflecting Reality: Enabling Diffusion Models to Produce Faithful Mirror Reflectionscited by 16
  6. 2024How Far are AI-generated Videos from Simulating the 3D Visual World: A Learned 3D Evaluation Approachcited by 15
  7. 2025Science-T2I: Addressing Scientific Illusions in Image Synthesiscited by 15
  8. 2024Synthetic Image Verification in the Era of Generative AI: What Works and What Isn't There Yetcited by 13
  9. 2024Multiview Equivariance Improves 3D Correspondence Understanding with Minimal Feature Finetuningcited by 13
  10. 2025Characterizing Photorealism and Artifacts in Diffusion Model-Generated Imagescited by 13
  11. 2025Survey on AI-Generated Media Detection: From Non-MLLM to MLLMcited by 12
  12. 2025FakeScope: Large Multimodal Expert Model for Transparent AI-Generated Image Forensicscited by 11
  13. 2025Materialist: Physically Based Editing Using Single-Image Inverse Renderingcited by 10
  14. 2025AI-GenBench: A New Ongoing Benchmark for AI-Generated Image Detectioncited by 10
  15. 2025LOTA: Bit-Planes Guided AI-Generated Image Detectioncited by 10
  16. 2025How Much 3D Do Video Foundation Models Encode?cited by 9
  17. 2024SEED4D: A Synthetic Ego--Exo Dynamic 4D Data Generator, Driving Dataset and Benchmarkcited by 8
  18. 2025MirrorVerse: Pushing Diffusion Models to Realistically Reflect the Worldcited by 8
  19. 2024Detecting Origin Attribution for Text-to-Image Diffusion Modelscited by 7
  20. 2024Unveiling Deep Shadows: A Survey and Benchmark on Image and Video Shadow Detection, Removal, and Generation in the Deep Learning Eracited by 6
  21. 2024Adversarial Robustness of AI-Generated Image Detectors in the Real Worldcited by 6
  22. 2025Fully AI-Generated Image Detection: Definition, Recent Advances and Challengescited by 4
  23. 2025Towards Reliable Identification of Diffusion-based Image Manipulationscited by 4
  24. 2025CHARM3R: Towards Unseen Camera Height Robust Monocular 3D Detectorcited by 4
  25. 2025REVEAL: Reasoning-Enhanced Forensic Evidence Analysis for Explainable AI-Generated Image Detectioncited by 4
  26. 2024Synthetic Photography Detection: A Visual Guidance for Identifying Synthetic Images Created by AIcited by 3
  27. 2024Quality Prediction of AI Generated Images and Videos: Emerging Trends and Opportunitiescited by 3
  28. 2024Nested Diffusion Models Using Hierarchical Latent Priorscited by 2
  29. 2025Generalized Design Choices for Deepfake Detectorscited by 2
  30. 2026Aggregating Diverse Cue Experts for AI-Generated Image Detectioncited by 2
  31. 2025PRADA: Probability-Ratio-Based Attribution and Detection of Autoregressive-Generated Imagescited by 1
  32. 2025ControlVP: Interactive Geometric Refinement of AI-Generated Images with Consistent Vanishing Pointscited by 1
  33. 2026ClueAegis: Heuristic-to-Reasoning Cognitive-skill Learning for Unified Evidence-based Synthetic Image Detectioncited by 1
  34. 2026Illusion or Integrity? Geometrical Consistency Metric for AIGC Video Quality Evaluationcited by 1
  35. 2026Shedding Light: A Benchmark for Evaluating Lighting Understanding in Generative Image Modelscited by 1
  36. 2026EIB-Net: Entropy-Guided Information Bottleneck for Generalizable AI-Generated Image Detectioncited by 1
  37. 2024At the edge of a generative cultural precipicecited by 0
  38. 2026DIAMOND-SSS: Diffusion-Augmented Multi-View Optimization for Data-efficient SubSurface Scatteringcited by 0

50 most cited of 61 All 61 (JSON)