mlsanityData to 14 Oct 2026

ExSinGAN: Learning an Explainable Generative Model from a Single Image

arXiv 2105.07350 ↗First posted 16 May 2021cs.CV cs.LGcited by 12

Not on the map. Why?

Abstract (arXiv)

Generating images from a single sample, as a newly developing branch of image synthesis, has attracted extensive attention. In this paper, we formulate this problem as sampling from the conditional distribution of a single image, and propose a hierarchical framework that simplifies the learning of the intricate conditional distributions through the successive learning of the distributions about structure, semantics and texture, making the process of learning and generation comprehensible. On this basis, we design ExSinGAN composed of three cascaded GANs for learning an explainable generative model from a given image, where the cascaded GANs model the distributions about structure, semantics and texture successively. ExSinGAN is learned not only from the internal patches of the given image as the previous works did, but also from the external prior obtained by the GAN inversion technique. Benefiting from the appropriate combination of internal and external information, ExSinGAN has a more powerful capability of generation and competitive generalization ability for the image manipulation tasks compared with prior works.

Key facts. Cited by 12 papers in the map (data through 14 Oct 2026). Builds on 38 of its 62 references that are in the map. First posted on arXiv 16 May 2021.

Builds on

38 of 62 references.

References · 38

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  3. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
  4. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,177
  5. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 7,005
  6. 2014Going Deeper with Convolutionscited by 4,241
  7. 2017Progressive Growing of GANs for Improved Quality, Stability, and Variationcited by 2,988
  8. 2016Perceptual Losses for Real-Time Style Transfer and Super-Resolutioncited by 2,694
  9. 2018Large Scale GAN Training for High Fidelity Natural Image Synthesiscited by 2,626
  10. 2017Improved Training of Wasserstein GANscited by 2,235
  11. 2015LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loopcited by 1,355
  12. 2017Deep Image Priorcited by 1,098
26 more
  1. 2019StarGAN v2: Diverse Image Synthesis for Multiple Domainscited by 1,098
  2. 2015Accurate Image Super-Resolution Using Very Deep Convolutional Networkscited by 903
  3. 2021GAN Inversion: A Surveycited by 367
  4. 2016Adversarial Feature Learningcited by 350
  5. 2016Generative Visual Manipulation on the Natural Image Manifoldcited by 348
  6. 2019SinGAN: Learning a Generative Model from a Single Natural Imagecited by 348
  7. 2017"Zero-Shot" Super-Resolution using Deep Internal Learningcited by 286
  8. 2019Large Scale Adversarial Representation Learningcited by 239
  9. 2020Exploiting Deep Generative Prior for Versatile Image Restoration and Manipulationcited by 225
  10. 2015Deep Generative Image Models using a Laplacian Pyramid of Adversarial Networkscited by 214
  11. 2016EnhanceNet: Single Image Super-Resolution Through Automated Texture Synthesiscited by 178
  12. 2020Semantic Photo Manipulation with a Generative Image Priorcited by 178
  13. 2016Semantic Image Inpainting with Deep Generative Modelscited by 157
  14. 2016Inverting The Generator Of A Generative Adversarial Networkcited by 140
  15. 2016Neural Photo Editing with Introspective Adversarial Networkscited by 109
  16. 2020Improved Techniques for Training Single-Image GANscited by 78
  17. 2020Transforming and Projecting Images into Class-conditional Generative Networkscited by 76
  18. 2020Positional Encoding as Spatial Inductive Bias in GANscited by 69
  19. 2018Non-Stationary Texture Synthesis by Adversarial Expansioncited by 67
  20. 2018Solving Linear Inverse Problems Using GAN Priors: An Algorithm with Provable Guaranteescited by 58
  21. 2021Drop the GAN: In Defense of Patches Nearest Neighbors as Single Image Generative Modelscited by 51
  22. 2020Hierarchical Patch VAE-GAN: Generating Diverse Videos from a Single Samplecited by 43
  23. 2021IMAGINE: Image Synthesis by Image-Guided Model Inversioncited by 25
  24. 2020Structural-analogy from a Single Image Paircited by 14
  25. 2020Generator Pyramid for High-Resolution Image Inpaintingcited by 2
  26. 2021Diverse Single Image Generation with Controllable Global Structurecited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 4; 2023: 5; 2024: 1; 2025: 1; 2026: 1.

12 papers.

  1. 2023Single Motion Diffusioncited by 65
  2. 2022SinDiffusion: Learning a Diffusion Model from a Single Natural Imagecited by 42
  3. 2023Towards Consistent Video Editing with Text-to-Image Diffusion Modelscited by 34
  4. 2023Sin3DM: Learning a Diffusion Model from a Single 3D Textured Shapecited by 29
  5. 2022Generalized One-shot Domain Adaptation of Generative Adversarial Networkscited by 19
  6. 2022PetsGAN: Rethinking Priors for Single Image Generationcited by 14
  7. 2023Image Synthesis under Limited Data: A Survey and Taxonomycited by 9
  8. 2025MotionDreamer: One-to-Many Motion Synthesis with Localized Generative Masked Transformercited by 9
  9. 2022One-shot Ultra-high-Resolution Generative Adversarial Network That Synthesizes 16K Images On A Single GPUcited by 1
  10. 2023TcGAN: Semantic-Aware and Structure-Preserved GANs with Individual Vision Transformer for Fast Arbitrary One-Shot Image Generationcited by 1
  11. 2024Towards Practical Single-shot Motion Synthesiscited by 1
  12. 2026FRPSS: Feature Rearrangement in Pre-Shape Space for Single-Image Generationcited by 0