mlsanityData to 14 Oct 2026

Comparison and Analysis of Image-to-Image Generative Adversarial Networks: A Survey

arXiv 2112.12625 ↗First posted 23 Dec 2021cs.CVcited by 11

Not on the map. Why?

Abstract (arXiv)

Generative Adversarial Networks (GANs) have recently introduced effective methods of performing Image-to-Image translations. These models can be applied and generalized to a variety of domains in Image-to-Image translation without changing any parameters. In this paper, we survey and analyze eight Image-to-Image Generative Adversarial Networks: Pix2Pix, CycleGAN, CoGAN, StarGAN, MUNIT, StarGAN2, DA-GAN, and Self Attention GAN. Each of these models presented state-of-the-art results and introduced new techniques to build Image-to-Image GANs. In addition to a survey of the models, we also survey the 18 datasets they were trained on and the 9 metrics they were evaluated on. Finally, we present results of a controlled experiment for 6 of these models on a common set of metrics and datasets. The results were mixed and showed that, on certain datasets, tasks, and metrics, some models outperformed others. The last section of this paper discusses those results and establishes areas of future research. As researchers continue to innovate new Image-to-Image GANs, it is important to gain a good understanding of the existing methods, datasets, and metrics. This paper provides a comprehensive overview and discussion to help build this foundation.

Key facts. Cited by 11 papers in the map (data through 14 Oct 2026). Builds on 31 of its 52 references that are in the map. First posted on arXiv 23 Dec 2021.

Builds on

31 of 52 references.

References · 31

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  3. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,177
  4. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 6,013
  5. 2016Image-to-Image Translation with Conditional Adversarial Networkscited by 4,527
  6. 2016The Cityscapes Dataset for Semantic Urban Scene Understandingcited by 4,444
  7. 2014Deep Learning Face Attributes in the Wildcited by 3,693
  8. 2019Analyzing and Improving the Image Quality of StyleGANcited by 3,588
  9. 2017Progressive Growing of GANs for Improved Quality, Stability, and Variationcited by 2,988
  10. 2016Improved Techniques for Training GANscited by 2,970
  11. 2016Perceptual Losses for Real-Time Style Transfer and Super-Resolutioncited by 2,694
  12. 2017Improved Training of Wasserstein GANscited by 2,235
19 more
  1. 2016Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Networkcited by 1,908
  2. 2018ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustnesscited by 1,432
  3. 2016Context Encoders: Feature Learning by Inpaintingcited by 1,428
  4. 2019StarGAN v2: Diverse Image Synthesis for Multiple Domainscited by 1,098
  5. 2017StarGAN: Unified Generative Adversarial Networks for Multi-Domain Image-to-Image Translationcited by 1,039
  6. 2018Self-Attention Generative Adversarial Networkscited by 809
  7. 2018Multimodal Unsupervised Image-to-Image Translationcited by 795
  8. 2017Unsupervised Image-to-Image Translation Networkscited by 603
  9. 2018Assessing Generative Models via Precision and Recallcited by 406
  10. 2017Toward Multimodal Image-to-Image Translationcited by 296
  11. 2018A Note on the Inception Scorecited by 226
  12. 2018Pros and Cons of GAN Evaluation Measurescited by 224
  13. 2016Coupled Generative Adversarial Networkscited by 216
  14. 2016Precomputed Real-Time Texture Synthesis with Markovian Generative Adversarial Networkscited by 192
  15. 2016Neural Photo Editing with Introspective Adversarial Networkscited by 109
  16. 2016Amortised MAP Inference for Image Super-resolutioncited by 68
  17. 2018DA-GAN: Instance-level Image Translation by Deep Attention Generative Adversarial Networks (with Supplementary Materials)cited by 21
  18. 2016Learning Temporal Transformations From Time-Lapse Videoscited by 7
  19. 2019Unsupervised Image-to-Image Translation with Self-Attention Networkscited by 3

Built on by

Cited by year

Citing papers per year: 2021: 1; 2022: 1; 2023: 1; 2024: 6; 2025: 2.

11 papers.

  1. 2024Fr'echet Radiomic Distance (FRD): A Versatile Metric for Comparing Medical Imaging Datasetscited by 19
  2. 2021Facial-Sketch Synthesis: A New Challengecited by 13
  3. 2024Improving 3D deep learning segmentation with biophysically motivated cell synthesiscited by 4
  4. 2025X-Edit: Detecting and Localizing Edits in Images Altered by Text-Guided Diffusion Modelscited by 3
  5. 2022Ensuring accurate stain reproduction in deep generative networks for virtual immunohistochemistrycited by 2
  6. 2023LatentAugment: Data Augmentation via Guided Manipulation of GAN's Latent Spacecited by 2
  7. 2024ResNCT: A Deep Learning Model for the Synthesis of Nephrographic Phase Images in CT Urographycited by 1
  8. 2024Reviewing FID and SID Metrics on Generative Adversarial Networkscited by 0
  9. 2024Improving Deep Generative Models on Many-To-One Image-to-Image Translationcited by 0
  10. 2024Multi-Style Facial Sketch Synthesis through Masked Generative Modelingcited by 0
  11. 2025Testing chatbots on the creation of encoders for audio conditioned image generationcited by 0