AI Paper Atlas

Research map / Image generation / GANs

Text2Scene: Generating Compositional Scenes From Textual Descriptions

Fuwen Tan, Song Feng, Vicente Ordonez

CVPR 2019 · Image generation › GANs · approach: GAN-based image manipulation · 99 citations (OpenAlex)

Check your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Add object and attribute attention instead of using no attention (ablation)Text2Scene · Abstract Scenes testU-obj precision: 0.665 -> 0.760Improved
Add dedicated attribute attention to object attention (ablation)Text2Scene · Abstract Scenes testU-obj precision: 0.731 -> 0.760Improved
Add attention regularization (ablation)Text2Scene · Abstract Scenes testU-obj precision: 0.749 -> 0.760Improved
Add object and attribute attention instead of using no attention (ablation)Text2Scene · COCO val2017CIDEr: 0.531 -> 0.601Improved
Add dedicated attribute attention to object attention (ablation)Text2Scene · COCO val2017CIDEr: 0.524 -> 0.601Improved
Add attention regularization (ablation)Text2Scene · COCO val2017CIDEr: 0.555 -> 0.601Improved
Add regression-based inpainting post-processing (ablation)Text2Scene synthetic composites · COCO val2014Inception Score: 22.33±1.58 -> 24.77±1.59Improved
Generate composite images with Text2Scene rather than competing methodsText2Scene · COCO val2014 human comparisonPreference ratio over AttnGAN: 0.7588Improved

Later papers that compared with this method

1 later accepted paper reports Text2Scene as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy