mlsanityData to 7 Oct 2026

ManiGAN: Text-Guided Image Manipulation

arXiv 1912.06203 ↗First posted 12 Dec 2019cs.CV cs.CL cs.LGcited by 156

Not on the map. Why?

Cited by 29 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

The goal of our paper is to semantically edit parts of an image matching a given text that describes desired attributes (e.g., texture, colour, and background), while preserving other contents that are irrelevant to the text. To achieve this, we propose a novel generative adversarial network (ManiGAN), which contains two key components: text-image affine combination module (ACM) and detail correction module (DCM). The ACM selects image regions relevant to the given text and then correlates the regions with corresponding semantic words for effective manipulation. Meanwhile, it encodes original image features to help reconstruct text-irrelevant contents. The DCM rectifies mismatched attributes and completes missing contents of the synthetic image. Finally, we suggest a new metric for evaluating image manipulation results, in terms of both the generation of new attributes and the reconstruction of text-irrelevant contents. Extensive experiments on the CUB and COCO datasets demonstrate the superior performance of the proposed method. Code is available at https://github.com/mrlibw/ManiGAN.

Key facts. Cited by 156 papers in the map (data through 7 Oct 2026). First posted on arXiv 12 Dec 2019.

Builds on

No reference list yet.

Built on by

Cited by year

Citing papers per year: 2021: 33; 2022: 35; 2023: 59; 2024: 20; 2025: 9.

156 papers.

Sort:

By area:

  1. 2021StyleCLIP: Text-Driven Manipulation of StyleGAN Imagerycited by 990
  2. 2023MasaCtrl: Tuning-Free Mutual Self-Attention Control for Consistent Image Synthesis and Editingcited by 722
  3. 2023Visual ChatGPT: Talking, Drawing and Editing with Visual Foundation Modelscited by 659
  4. 2022DiffEdit: Diffusion-based semantic image editing with mask guidancecited by 643
  5. 2023MagicBrush: A Manually Annotated Dataset for Instruction-Guided Image Editingcited by 615
  6. 2021CLIP-NeRF: Text-and-Image Driven Manipulation of Neural Radiance Fieldscited by 369
  7. 2021GAN Inversion: A Surveycited by 366
  8. 2022Text2LIVE: Text-Driven Layered Image and Video Editingcited by 312
  9. 2022VQGAN-CLIP: Open Domain Image Generation and Editing with Natural Language Guidancecited by 285
  10. 2022Imagen Editor and EditBench: Advancing and Evaluating Text-Guided Image Inpaintingcited by 229
  11. 2021More Control for Free! Image Synthesis with Semantic Diffusion Guidancecited by 211
  12. 2021CLIPstyler: Image Style Transfer with a Single Text Conditioncited by 203
38 more
  1. 2023Guiding Instruction-based Image Editing via Multimodal Large Language Modelscited by 182
  2. 2021PSCC-Net: Progressive Spatio-Channel Correlation Network for Image Manipulation Detection and Localizationcited by 133
  3. 2021Image-to-Image Translation: Methods and Applicationscited by 116
  4. 2022Uncovering the Disentanglement Capability in Text-to-Image Diffusion Modelscited by 116
  5. 2023Collaborative Diffusion for Multi-Modal Face Generation and Editingcited by 116
  6. 2021Talk-to-Edit: Fine-Grained Facial Editing via Dialogcited by 102
  7. 2022EnvEdit: Environment Editing for Vision-and-Language Navigationcited by 83
  8. 2021Explainability of deep vision-based autonomous driving systems: Review and challengescited by 80
  9. 2022ObjectFormer for Image Manipulation Detection and Localizationcited by 78
  10. 2023DisenBooth: Identity-Preserving Disentangled Tuning for Subject-Driven Text-to-Image Generationcited by 75
  11. 2022Towards Implicit Text-Guided 3D Shape Generationcited by 68
  12. 2023Shape-aware Text-driven Layered Video Editingcited by 54
  13. 2021Adversarial Text-to-Image Synthesis: A Reviewcited by 52
  14. 2022SinDiffusion: Learning a Diffusion Model from a Single Natural Imagecited by 42
  15. 2021StyleMC: Multi-Channel Based Fast Text-Guided Image Generation and Manipulationcited by 40
  16. 2023DreamEdit: Subject-driven Image Editingcited by 37
  17. 2021M6-UFC: Unifying Multi-Modal Controls for Conditional Image Synthesis via Non-Autoregressive Generative Transformerscited by 36
  18. 2021Language-Driven Image Style Transfercited by 36
  19. 2021Sound-Guided Semantic Image Manipulationcited by 35
  20. 2021Predict, Prevent, and Evaluate: Disentangled Text-Driven Image Manipulation Empowered by Pre-Trained Vision-Language Modelcited by 34
  21. 2022CLIPVG: Text-Guided Image Manipulation Using Differentiable Vector Graphicscited by 34
  22. 2022AnyFace: Free-style Text-to-Face Synthesis and Manipulationcited by 33
  23. 2021Collaborative Spatial-Temporal Modeling for Language-Queried Video Actor Segmentationcited by 32
  24. 2023Text-Driven Image Editing via Learnable Regionscited by 31
  25. 2025InstructX: Towards Unified Visual Editing with MLLM Guidancecited by 31
  26. 2022FlexIT: Towards Flexible Semantic Image Translationcited by 28
  27. 2021Cycle-Consistent Inverse GAN for Text-to-Image Synthesiscited by 27
  28. 2022ISS: Image as Stepping Stone for Text-Guided 3D Shape Generationcited by 27
  29. 2023Multi-modal Machine Learning in Engineering Design: A Review and Future Directionscited by 27
  30. 2023DeltaEdit: Exploring Text-free Training for Text-Driven Image Manipulationcited by 27
  31. 2023Blending-NeRF: Text-Driven Localized Editing in Neural Radiance Fieldscited by 27
  32. 2023Temporal Collection and Distribution for Referring Video Object Segmentationcited by 27
  33. 2023TextFusion: Unveiling the Power of Textual Semantics for Controllable Image Fusioncited by 26
  34. 2021Towards Open-World Text-Guided Face Image Generation and Manipulationcited by 25
  35. 2021Learning by Planning: Language-Guided Global Image Editingcited by 25
  36. 2023Region-Aware Diffusion for Zero-shot Text-driven Image Editingcited by 25
  37. 2023AI-Generated Content (AIGC) for Various Data Modalities: A Surveycited by 25
  38. 2023Towards Generic Image Manipulation Detection with Weakly-Supervised Self-Consistency Learningcited by 23

50 most cited of 156 All 156 (JSON)