mlsanityData to 14 Oct 2026

Improved Techniques for Training Single-Image GANs

arXiv 2003.11512 ↗First posted 25 Mar 2020cs.CVcited by 78

Not on the map. Why?

Abstract (arXiv)

Recently there has been an interest in the potential of learning generative models from a single image, as opposed to from a large dataset. This task is of practical significance, as it means that generative models can be used in domains where collecting a large dataset is not feasible. However, training a model capable of generating realistic images from only a single sample is a difficult problem. In this work, we conduct a number of experiments to understand the challenges of training these methods and propose some best practices that we found allowed us to generate improved results over previous work in this space. One key piece is that unlike prior single image generation methods, we concurrently train several stages in a sequential multi-stage manner, allowing us to learn models with fewer stages of increasing image resolution. Compared to a recent state of the art baseline, our model is up to six times faster to train, has fewer parameters, and can better capture the global structure of images.

Key facts. Cited by 78 papers in the map (data through 14 Oct 2026). First posted on arXiv 25 Mar 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 14; 2022: 22; 2023: 15; 2024: 9; 2025: 10; 2026: 8.

78 papers.

Sort:

By area:

  1. 2023DynamiCrafter: Animating Open-domain Images with Video Diffusion Priorscited by 471
  2. 2023Single Motion Diffusioncited by 65
  3. 2021InfinityGAN: Towards Infinite-Pixel Image Synthesiscited by 61
  4. 2022SinDDM: A Single Image Denoising Diffusion Modelcited by 60
  5. 2022SinFusion: Training Diffusion Models on a Single Image or Videocited by 58
  6. 2024CRS-Diff: Controllable Remote Sensing Image Generation with Diffusion Modelcited by 55
  7. 2024Follow-Your-Click: Open-domain Regional Image Animation via Short Promptscited by 52
  8. 2021Drop the GAN: In Defense of Patches Nearest Neighbors as Single Image Generative Modelscited by 51
  9. 2022SinDiffusion: Learning a Diffusion Model from a Single Natural Imagecited by 42
  10. 2022Learning to Generate 3D Shapes from a Single Examplecited by 31
  11. 2023Sin3DM: Learning a Diffusion Model from a Single 3D Textured Shapecited by 29
  12. 2022Generating natural images with direct Patch Distributions Matchingcited by 27
38 more
  1. 2025Human Motion Video Generation: A Surveycited by 25
  2. 2022GANimator: Neural Motion Synthesis from a Single Sequencecited by 23
  3. 2022A Comprehensive Survey on Data-Efficient GANs in Image Generationcited by 20
  4. 2022SeamlessGAN: Self-Supervised Synthesis of Tileable Texture Mapscited by 19
  5. 2023A Survey on Generative Modeling with Limited Data, Few Shots, and Zero Shotcited by 19
  6. 2023Privacy Distillation: Reducing Re-identification Risk of Multimodal Diffusion Modelscited by 18
  7. 2021Few-shot Image Generation with Mixup-based Distance Learningcited by 16
  8. 2023Patch-based 3D Natural Scene Generation from a Single Examplecited by 15
  9. 2022PetsGAN: Rethinking Priors for Single Image Generationcited by 14
  10. 2021Diverse Generation from a Single Video Made Possiblecited by 13
  11. 2025AGHI-QA: A Subjective-Aligned Dataset and Metric for AI-Generated Human Imagescited by 13
  12. 2021ExSinGAN: Learning an Explainable Generative Model from a Single Imagecited by 12
  13. 2022SinGRAF: Learning a 3D Generative Radiance Field for a Single Scenecited by 11
  14. 2023Single Mesh Diffusion Models with Field Latents for Texture Generationcited by 11
  15. 2021Lifelong Mixture of Variational Autoencoderscited by 10
  16. 2021CharacterGAN: Few-Shot Keypoint Character Animation and Reposingcited by 9
  17. 2021MOGAN: Morphologic-structure-aware Generative Learning from a Single Imagecited by 9
  18. 20223inGAN: Learning a 3D Generative Model from Images of a Self-similar Scenecited by 9
  19. 2023Fast Inference in Denoising Diffusion Models via MMD Finetuningcited by 9
  20. 2023Image Synthesis under Limited Data: A Survey and Taxonomycited by 9
  21. 2025MotionDreamer: One-to-Many Motion Synthesis with Localized Generative Masked Transformercited by 9
  22. 2021Generating Novel Scene Compositions from Single Images and Videoscited by 8
  23. 2021Meta Internal Learningcited by 7
  24. 2024A Survey of Few-Shot Learning for Biomedical Time Seriescited by 7
  25. 2022Hiding Images in Deep Probabilistic Modelscited by 5
  26. 2026Nucleus-Image: Sparse MoE for Image Generationcited by 5
  27. 2022OSSGAN: Open-Set Semi-Supervised Image Generationcited by 4
  28. 2022One-Shot Synthesis of Images and Segmentation Maskscited by 4
  29. 20223D Brain and Heart Volume Generative Models: A Surveycited by 4
  30. 2024Better Fit: Accommodate Variations in Clothing Types for Virtual Try-oncited by 4
  31. 2021Learning to Generate Novel Scene Compositions from Single Images and Videoscited by 3
  32. 2022ASSET: Autoregressive Semantic Scene Editing with Transformers at High Resolutionscited by 3
  33. 2025ShapeShifter: 3D Variations Using Multiscale and Sparse Point-Voxel Diffusioncited by 3
  34. 2021Diverse Single Image Generation with Controllable Global Structurecited by 2
  35. 2022Improve Generalization of Driving Policy at Signalized Intersections with Adversarial Learningcited by 2
  36. 2022ScoreMix: A Scalable Augmentation Strategy for Training GANs with Limited Datacited by 2
  37. 2022BlendGAN: Learning and Blending the Internal Distributions of Single Images by Spatial Image-Identity Conditioningcited by 2
  38. 2024LookupForensics: A Large-Scale Multi-Task Dataset for Multi-Phase Image-Based Fact Verificationcited by 2

50 most cited of 78 All 78 (JSON)