mlsanityData to 14 Oct 2026

StackGAN++: Realistic Image Synthesis with Stacked Generative Adversarial Networks

arXiv 1710.10916 ↗First posted 19 Oct 2017cs.CV cs.AI stat.MLcited by 229

Not on the map. Why?

Cited by 38 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Although Generative Adversarial Networks (GANs) have shown remarkable success in various tasks, they still face challenges in generating high quality images. In this paper, we propose Stacked Generative Adversarial Networks (StackGAN) aiming at generating high-resolution photo-realistic images. First, we propose a two-stage generative adversarial network architecture, StackGAN-v1, for text-to-image synthesis. The Stage-I GAN sketches the primitive shape and colors of the object based on given text description, yielding low-resolution images. The Stage-II GAN takes Stage-I results and text descriptions as inputs, and generates high-resolution images with photo-realistic details. Second, an advanced multi-stage generative adversarial network architecture, StackGAN-v2, is proposed for both conditional and unconditional generative tasks. Our StackGAN-v2 consists of multiple generators and discriminators in a tree-like structure; images at multiple scales corresponding to the same scene are generated from different branches of the tree. StackGAN-v2 shows more stable training behavior than StackGAN-v1 by jointly approximating multiple distributions. Extensive experiments demonstrate that the proposed stacked generative adversarial networks significantly outperform other state-of-the-art methods in generating photo-realistic images.

Key facts. Cited by 229 papers in the map (data through 14 Oct 2026). First posted on arXiv 19 Oct 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 60; 2022: 66; 2023: 68; 2024: 18; 2025: 14; 2026: 3.

229 papers.

Sort:

By area:

  1. 2021Zero-Shot Text-to-Image Generationcited by 4,288
  2. 2022Scaling Autoregressive Models for Content-Rich Text-to-Image Generationcited by 1,295
  3. 2021Transformers in Vision: A Surveycited by 1,013
  4. 2021Vector Quantized Diffusion Model for Text-to-Image Synthesiscited by 774
  5. 2023MasaCtrl: Tuning-Free Mutual Self-Attention Control for Consistent Image Synthesis and Editingcited by 727
  6. 2022Blended Latent Diffusioncited by 432
  7. 2023Training-Free Layout Control with Cross-Attention Guidancecited by 313
  8. 2022Text2LIVE: Text-Driven Layered Image and Video Editingcited by 312
  9. 2022MAXIM: Multi-Axis MLP for Image Processingcited by 302
  10. 2023Break-A-Scene: Extracting Multiple Concepts from a Single Imagecited by 231
  11. 2021CLIPstyler: Image Style Transfer with a Single Text Conditioncited by 203
  12. 2022ReCo: Region-Controlled Text-to-Image Generationcited by 179
38 more
  1. 2024Lotus: Diffusion-based Visual Foundation Model for High-quality Dense Predictioncited by 166
  2. 2022Vision-Language Pre-training: Basics, Recent Advances, and Future Trendscited by 117
  3. 2021Paint by Wordcited by 107
  4. 2023GALIP: Generative Adversarial CLIPs for Text-to-Image Synthesiscited by 85
  5. 2023A Complete Survey on Generative AI (AIGC): Is ChatGPT from GPT-4 to GPT-5 All You Need?cited by 84
  6. 2023PanoGen: Text-Conditioned Panoramic Environment Generation for Vision-and-Language Navigationcited by 77
  7. 2023Intelligent Grimm -- Open-ended Visual Storytelling via Latent Diffusion Modelscited by 77
  8. 2022Frido: Feature Pyramid Diffusion for Complex Scene Image Synthesiscited by 75
  9. 2021Learning to Compose Visual Relationscited by 72
  10. 2023Toward Verifiable and Reproducible Human Evaluation for Text-to-Image Generationcited by 68
  11. 2021Improving Text-to-Image Synthesis Using Contrastive Learningcited by 62
  12. 2023Prompt-Free Diffusion: Taking "Text" out of Text-to-Image Diffusion Modelscited by 62
  13. 2022CLIP-GEN: Language-Free Training of a Text-to-Image Generator with CLIPcited by 60
  14. 2021Conditional Deformable Image Registration with Convolutional Neural Networkcited by 59
  15. 2021Generating images from caption and vice versa via CLIP-Guided Generative Latent Space Searchcited by 57
  16. 2023LLM Blueprint: Enabling Text-to-Image Generation with Complex and Detailed Promptscited by 54
  17. 2021Text to Image Generation with Semantic-Spatial Aware GANcited by 53
  18. 2021Adversarial Text-to-Image Synthesis: A Reviewcited by 52
  19. 2021LatentCLR: A Contrastive Learning Approach for Unsupervised Discovery of Interpretable Directionscited by 52
  20. 2021Multimodal Image Synthesis and Editing: The Generative AI Eracited by 52
  21. 2021Efficient Feature Transformations for Discriminative and Generative Continual Learningcited by 50
  22. 2022Deepfake Network Architecture Attributioncited by 47
  23. 2023RenAIssance: A Survey into AI Text-to-Image Generation in the Era of Large Modelcited by 47
  24. 2021DAE-GAN: Dynamic Aspect-aware GAN for Text-to-Image Synthesiscited by 45
  25. 2022Discrete Contrastive Diffusion for Cross-Modal Music and Image Generationcited by 44
  26. 2021StyleMC: Multi-Channel Based Fast Text-Guided Image Generation and Manipulationcited by 40
  27. 2023StyleAdapter: A Unified Stylized Image Generation Modelcited by 39
  28. 2021DivCo: Diverse Conditional Image Synthesis via Contrastive Generative Adversarial Networkcited by 37
  29. 2023X-Mesh: Towards Fast and Accurate Text-driven 3D Stylization via Dynamic Textual Guidancecited by 37
  30. 2021M6-UFC: Unifying Multi-Modal Controls for Conditional Image Synthesis via Non-Autoregressive Generative Transformerscited by 36
  31. 2023Sketch and Text Guided Diffusion Model for Colored Point Cloud Generationcited by 36
  32. 2021Selective Synthetic Augmentation with HistoGAN for Improved Histopathology Image Classificationcited by 35
  33. 2023High-Fidelity 3D Face Generation from Natural Language Descriptionscited by 33
  34. 2021Visually grounded models of spoken language: A survey of datasets, architectures and evaluation techniquescited by 32
  35. 2022VAEL: Bridging Variational Autoencoders and Probabilistic Logic Programmingcited by 31
  36. 2021Dual Contrastive Loss and Attention for GANscited by 30
  37. 2022SceneTrilogy: On Human Scene-Sketch and its Complementarity with Photo and Textcited by 30
  38. 2021Cycle-Consistent Inverse GAN for Text-to-Image Synthesiscited by 27

50 most cited of 229 All 229 (JSON)