arbitrary-text-to-image-papers
A collection of arbitrary kinds of text to image papers, organized by Tzu-Heng Lin and Haoran Mo.
Papers are ordered in arXiv first version submitting time (if applicable).
Feel free to send a PR or an issue.
TOC
general text to image
| Note | Model | Paper | Conference | paper link | code link |
|---|---|---|---|---|---|
| GAN-INT-CLS | Generative Adversarial Text to Image Synthesis | ICML 2016 | 1605.05396 | reedscot/icml2016 | |
| StackGAN | StackGAN: Text to Photo-realistic Image Synthesis with Stacked Generative Adversarial Networks | ICCV 2017 | 1612.03242 | hanzhanggit/StackGAN | |
| StackGAN++ | StackGAN++: Realistic Image Synthesis with Stacked Generative Adversarial Networks | TPAMI 2018 | 1710.10916 | hanzhanggit/StackGAN-v2 | |
| AttnGAN | AttnGAN: Fine-Grained Text to Image Generation with Attentional Generative Adversarial Networks | CVPR 2018 | 1711.10485 | taoxugit/AttnGAN | |
| HD-GAN | Photographic Text-to-Image Synthesis with a Hierarchically-nested Adversarial Network | CVPR 2018 | 1802.09178 | ypxie/HDGan | |
| StoryGAN | StoryGAN: A Sequential Conditional GAN for Story Visualization | CVPR 2019 | 1812.02784 | yitong91/StoryGAN | |
| MirrorGAN | MirrorGAN: Learning Text-to-image Generation by Redescription | CVPR 2019 | 1903.05854 | ||
| DM-GAN | DM-GAN: Dynamic Memory Generative Adversarial Networks for Text-to-Image Synthesis | CVPR 2019 | 1904.01310 | ||
| SD-GAN | Semantics Disentangling for Text-to-Image Generation | CVPR 2019 | 1904.01480 |
scene graph/layout to image
| Note | Model | Paper | Conference | paper link | code link |
|---|---|---|---|---|---|
| GAWWN | Learning What and Where to Draw | NIPS 2016 | 1610.02454 | reedscot/nips2016 | |
| Inferring Semantic Layout for Hierarchical Text-to-Image Synthesis | CVPR 2018 | 1801.05091 | |||
| sg2im | Image Generation from Scene Graphs | CVPR 2018 | 1804.01622 | google/sg2im | |
| Text2Scene | Text2Scene: Generating Abstract Scenes from Textual Descriptions | CVPR 2019 | 1809.01110 | uvavision/Text2Image | |
| Layout2Im | Image Generation from Layout | CVPR 2019 | 1811.11389 | ||
| LayoutGAN | LayoutGAN: Generating Graphic Layouts with Wireframe Discriminator | ICLR 2019 | openreview | ||
| Object Pathways | Generating Multiple Objects at Spatially Distinct Locations | ICLR 2019 | 1901.00686 | tohinz/multiple-objects-gan | |
| Using Scene Graph Context to Improve Image Generation | 1901.03762 | ||||
| Obj-GAN | Object-driven Text-to-Image Synthesis via Adversarial Training | CVPR 2019 | 1902.10740 | jamesli1618/Obj-GAN |
dialog to image
| Note | Model | Paper | Conference | paper link | code link |
|---|---|---|---|---|---|
| CoDraw | CoDraw: Visual Dialog for Collaborative Drawing | 1712.05558 | CoDraw dataset | ||
| ChatPainter | ChatPainter: Improving Text to Image Generation using Dialogue | ICLRW 2018 | 1802.08216 | ||
| Keep Drawing It: Iterative language-based image generation and editing | NIPSW 2018 | 1811.09845 | CLEVR dataset | ||
| Chat-crowd | Chat-crowd: A Dialog-based Platform for Visual Layout Composition | 1812.04081 | uvavision/chat-crowd | ||
| SeqAttnGAN | Sequential Attention GAN for Interactive Image Editing via Dialogue | 1812.08352 |