mlsanityData to 14 Oct 2026

Text-Adaptive Generative Adversarial Networks: Manipulating Images with Natural Language

arXiv 1810.11919 ↗First posted 29 Oct 2018cs.CVcited by 90

Not on the map. Why?

Abstract (arXiv)

This paper addresses the problem of manipulating images using natural language description. Our task aims to semantically modify visual attributes of an object in an image according to the text describing the new visual appearance. Although existing methods synthesize images having new attributes, they do not fully preserve text-irrelevant contents of the original image. In this paper, we propose the text-adaptive generative adversarial network (TAGAN) to generate semantically manipulated images while preserving text-irrelevant contents. The key to our method is the text-adaptive discriminator that creates word-level local discriminators according to input text to classify fine-grained attributes independently. With this discriminator, the generator learns to generate images where only regions that correspond to the given text are modified. Experimental results show that our method outperforms existing methods on CUB and Oxford-102 datasets, and our results were mostly preferred on a user study. Extensive analysis shows that our method is able to effectively disentangle visual attributes and produce pleasing outputs.

Key facts. Cited by 90 papers in the map (data through 14 Oct 2026). First posted on arXiv 29 Oct 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 23; 2022: 21; 2023: 32; 2024: 9; 2025: 4; 2026: 1.

90 papers.

Sort:

By area:

  1. 2021StyleCLIP: Text-Driven Manipulation of StyleGAN Imagerycited by 991
  2. 2023MasaCtrl: Tuning-Free Mutual Self-Attention Control for Consistent Image Synthesis and Editingcited by 727
  3. 2022Text2LIVE: Text-Driven Layered Image and Video Editingcited by 312
  4. 2022VQGAN-CLIP: Open Domain Image Generation and Editing with Natural Language Guidancecited by 285
  5. 2021More Control for Free! Image Synthesis with Semantic Diffusion Guidancecited by 212
  6. 2023Guiding Instruction-based Image Editing via Multimodal Large Language Modelscited by 185
  7. 2021Talk-to-Edit: Fine-Grained Facial Editing via Dialogcited by 102
  8. 2022EnvEdit: Environment Editing for Vision-and-Language Navigationcited by 83
  9. 2023Shape-aware Text-driven Layered Video Editingcited by 54
  10. 2021Adversarial Text-to-Image Synthesis: A Reviewcited by 52
  11. 2021Improving Generation and Evaluation of Visual Stories via Semantic Consistencycited by 43
  12. 2021StyleMC: Multi-Channel Based Fast Text-Guided Image Generation and Manipulationcited by 40
38 more
  1. 2023Highly Personalized Text Embedding for Image Manipulation by Stable Diffusioncited by 39
  2. 2021Language-Driven Image Style Transfercited by 37
  3. 2021M6-UFC: Unifying Multi-Modal Controls for Conditional Image Synthesis via Non-Autoregressive Generative Transformerscited by 36
  4. 2021Sound-Guided Semantic Image Manipulationcited by 35
  5. 2021Predict, Prevent, and Evaluate: Disentangled Text-Driven Image Manipulation Empowered by Pre-Trained Vision-Language Modelcited by 34
  6. 2022AnyFace: Free-style Text-to-Face Synthesis and Manipulationcited by 33
  7. 2025InstructX: Towards Unified Visual Editing with MLLM Guidancecited by 32
  8. 2023DeltaEdit: Exploring Text-free Training for Text-Driven Image Manipulationcited by 27
  9. 2021DeFLOCNet: Deep Image Editing via Flexible Low-level Controlscited by 26
  10. 2021Towards Open-World Text-Guided Face Image Generation and Manipulationcited by 25
  11. 2021Learning by Planning: Language-Guided Global Image Editingcited by 25
  12. 2023Region-Aware Diffusion for Zero-shot Text-driven Image Editingcited by 25
  13. 2023A Comprehensive Overview and Comparative Analysis on Deep Learning Models: CNN, RNN, LSTM, GRUcited by 25
  14. 2022One Model to Edit Them All: Free-Form Text-Driven Image Manipulation with Semantic Modulationscited by 24
  15. 2022Word-Level Fine-Grained Story Visualizationcited by 23
  16. 2022Learning Visual Styles from Audio-Visual Associationscited by 22
  17. 2023KV Inversion: KV Embeddings Learning for Text-Conditioned Real Image Action Editingcited by 22
  18. 2021Embedding Arithmetic of Multimodal Queries for Image Retrievalcited by 21
  19. 2023FICE: Text-Conditioned Fashion Image Editing With Guided GAN Inversioncited by 21
  20. 2021Towers of Babel: Combining Images, Language, and 3D Geometry for Learning Multimodal Visioncited by 18
  21. 2023Fine-grained Audible Video Descriptioncited by 18
  22. 2023Language-guided Human Motion Synthesis with Atomic Actionscited by 17
  23. 2023ChatFace: Chat-Guided Real Face Editing via Diffusion Latent Space Manipulationcited by 16
  24. 2023Adversarial Score Distillation: When score distillation meets GANcited by 15
  25. 2023Dynamic Weighted Combiner for Mixed-Modal Image Retrievalcited by 15
  26. 2021CLEVR_HYP: A Challenge Dataset and Baselines for Visual Question Answering with Hypothetical Actions over Imagescited by 14
  27. 2024SignAvatar: Sign Language 3D Motion Reconstruction and Generationcited by 14
  28. 2022ManiTrans: Entity-Level Text-Guided Image Manipulation via Token-wise Semantic Alignment and Generationcited by 13
  29. 2022DE-Net: Dynamic Text-guided Image Editing Adversarial Networkscited by 12
  30. 2023Text-to-image Editing by Image Information Removalcited by 12
  31. 2023Tuning-Free Inversion-Enhanced Control for Consistent Image Editingcited by 12
  32. 2021AttrLostGAN: Attribute Controlled Image Synthesis from Reconfigurable Layout and Stylecited by 11
  33. 2022Memory-Driven Text-to-Image Generationcited by 10
  34. 2021Unified Questioner Transformer for Descriptive Question Generation in Goal-Oriented Visual Dialoguecited by 8
  35. 2023Vision + Language Applications: A Surveycited by 8
  36. 2022Robust Sound-Guided Image Manipulationcited by 7
  37. 2023Text-driven Visual Synthesis with Latent Diffusion Priorcited by 6
  38. 2023Language-based Photo Color Adjustment for Graphic Designscited by 6

50 most cited of 90 All 90 (JSON)