mlsanityData to 14 Oct 2026

Diverse Image Synthesis from Semantic Layouts via Conditional IMLE

arXiv 1811.12373 ↗First posted 29 Nov 2018cs.CV cs.GR cs.LGcited by 60

Not on the map. Why?

Abstract (arXiv)

Most existing methods for conditional image synthesis are only able to generate a single plausible image for any given input, or at best a fixed number of plausible images. In this paper, we focus on the problem of generating images from semantic segmentation maps and present a simple new method that can generate an arbitrary number of images with diverse appearance for the same semantic layout. Unlike most existing approaches which adopt the GAN framework, our method is based on the recently introduced Implicit Maximum Likelihood Estimation (IMLE) framework. Compared to the leading approach, our method is able to generate more diverse images while producing fewer artifacts despite using the same architecture. The learned latent space also has sensible structure despite the lack of supervision that encourages such behaviour. Videos and code are available at https://people.eecs.berkeley.edu/~ke.li/projects/imle/scene_layouts/.

Key facts. Cited by 60 papers in the map (data through 14 Oct 2026). First posted on arXiv 29 Nov 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 13; 2022: 8; 2023: 6; 2024: 13; 2025: 13; 2026: 7.

60 papers.

Sort:

By area:

  1. 2023Towards Universal Fake Image Detectors that Generalize Across Generative Modelscited by 490
  2. 2022DE-FAKE: Detection and Attribution of Fake Images Generated by Text-to-Image Generation Modelscited by 168
  3. 2022Semantic Image Synthesis via Diffusion Modelscited by 132
  4. 2024C2P-CLIP: Injecting Category Common Prompt in CLIP to Enhance Generalization in Deepfake Detectioncited by 113
  5. 2024Orthogonal Subspace Decomposition for Generalizable AI-Generated Image Detectioncited by 105
  6. 2024Leveraging Representations from Intermediate Encoder-blocks for Synthetic Image Detectioncited by 89
  7. 2022Fusing Global and Local Features for Generalized AI-Synthesized Image Detectioncited by 88
  8. 2021A Closer Look at Fourier Spectrum Discrepancies for CNN-generated Images Detectioncited by 68
  9. 2022Towards Implicit Text-Guided 3D Shape Generationcited by 68
  10. 2021Countering Malicious DeepFakes: Survey, Battleground, and Horizoncited by 56
  11. 2024Real-Time Deepfake Detection in the Real-Worldcited by 51
  12. 2024Community Forensics: Using Thousands of Generators to Train Fake Image Detectorscited by 50
38 more
  1. 2023Generalizable Synthetic Image Detection via Language-guided Contrastive Learningcited by 49
  2. 2021Image Synthesis via Semantic Compositioncited by 45
  3. 2022A Continual Deepfake Detection Benchmark: Dataset, Methods, and Essentialscited by 45
  4. 2024D3: Scaling Up Deepfake Detection by Learning from Discrepancycited by 45
  5. 2023GenDet: Towards Good Generalizations for AI-Generated Image Detectioncited by 36
  6. 2022BlobGAN: Spatially Disentangled Scene Representationscited by 35
  7. 2025MoFlow: One-Step Flow Matching for Human Trajectory Forecasting via Implicit Maximum Likelihood Estimation based Distillationcited by 31
  8. 2021Learning by Planning: Language-Guided Global Image Editingcited by 25
  9. 2023Level Up the Deepfake Detection: a Method to Effectively Discriminate Images Generated by GAN Architectures and Diffusion Modelscited by 21
  10. 2024Mixture of Low-rank Experts for Transferable AI-Generated Image Detectioncited by 21
  11. 2021Learning to Disentangle GAN Fingerprint for Fake Image Attributioncited by 20
  12. 2024SemFlow: Binding Semantic Segmentation and Image Synthesis via Rectified Flowcited by 20
  13. 2022Retrieval-based Spatially Adaptive Normalization for Semantic Image Synthesiscited by 15
  14. 2024ForgeLens: Data-Efficient Forgery Focus for Generalizable Forgery Image Detectioncited by 15
  15. 2023Ten Years of Generative Adversarial Nets (GANs): A survey of the state-of-the-artcited by 14
  16. 2025Methods and Trends in Detecting AI-Generated Images: A Comprehensive Reviewcited by 12
  17. 2021MCL-GAN: Generative Adversarial Networks with Multiple Specialized Discriminatorscited by 11
  18. 2025Stay-Positive: A Case for Ignoring Real Image Features in Fake Image Detectioncited by 11
  19. 2025Manifold Induced Biases for Zero-shot and Few-shot Detection of Generated Imagescited by 10
  20. 2025AI-GenBench: A New Ongoing Benchmark for AI-Generated Image Detectioncited by 10
  21. 2025Towards Generalizable AI-Generated Image Detection via Image-Adaptive Prompt Learningcited by 9
  22. 2025Symmetrical Flow Matching: Unified Image Generation, Segmentation, and Classification with Score-Based Generative Modelscited by 8
  23. 2021A-PixelHop: A Green, Robust and Explainable Fake-Image Detectorcited by 7
  24. 2024Automatic Controllable Colorization via Imaginationcited by 7
  25. 2026PGC: Peak-Guided Calibration for Generalizable AI-Generated Image Detectioncited by 6
  26. 2021Multimodal Shape Completion via IMLEcited by 5
  27. 2025AI-Generated Image Detection: An Empirical Study and Future Research Directionscited by 5
  28. 2021Few-shot Semantic Image Synthesis Using StyleGAN Priorcited by 4
  29. 2022Stay Positive: Non-Negative Image Synthesis for Augmented Realitycited by 4
  30. 2025SFLD: Reducing the content bias for AI-generated Image Detectioncited by 4
  31. 2024HyperDet: Generalizable Detection of Synthesized Images by Generating and Merging A Mixture of Hyper LoRAscited by 3
  32. 2023Inferring and Leveraging Parts from Object Shape for Improving Semantic Image Synthesiscited by 2
  33. 2025Leveraging Failed Samples: A Few-Shot and Training-Free Framework for Generalized Deepfake Detectioncited by 2
  34. 2025Semantic-Aware Reconstruction Error for Detecting AI-Generated Imagescited by 2
  35. 2026Do Transformations Reveal the Truth? Generative Residual Learning for Generalized AI-Generated Image Detectioncited by 2
  36. 2021Fake Visual Content Detection Using Two-Stream Convolutional Neural Networkscited by 1
  37. 2021[RE] CNN-generated images are surprisingly easy to spot...for nowcited by 1
  38. 2021Diversifying Semantic Image Synthesis and Editing via Class- and Layer-wise VAEscited by 1

50 most cited of 60 All 60 (JSON)