AI Paper Atlas

Research map / Image generation / GANs

StackGAN: Text to Photo-Realistic Image Synthesis With Stacked Generative Adversarial Networks

Han Zhang, Tao Xu, Hongsheng Li, Shaoting Zhang, Xiaogang Wang, Xiaolei Huang, Dimitris N. Metaxas

ICCV 2017 · Image generation › GANs · approach: Large-scale GAN latent analysis · 3,134 citations (OpenAlex)

Read the paperCheck 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 Stage-II refinement GAN on top of Stage-I (256x256) (ablation)StackGAN · CUBinception score: 3.02 -> 3.70Improved
add Conditioning Augmentation to 256x256 StackGAN (ablation)StackGAN 256x256 · CUBinception score: 3.31 -> 3.70Improved
add Conditioning Augmentation to 256x256 Stage-I GAN (ablation)Stage-I GAN · CUBinception score: 2.48 -> 3.02Improved
add Conditioning Augmentation to 64x64 Stage-I GAN (ablation)Stage-I GAN · CUBinception score: 2.66 -> 2.95Improved
add Conditioning Augmentation to 128x128 StackGAN (ablation)StackGAN 128x128 · CUBinception score: 3.20 -> 3.35Improved
input text again at Stage-II (256x256) (ablation)StackGAN 256x256 · CUBinception score: 3.45 -> 3.70Improved
input text again at Stage-II (128x128) (ablation)StackGAN 128x128 · CUBinception score: 3.13 -> 3.35Improved
increase output resolution from 128x128 to 256x256 (ablation)StackGAN · CUBinception score: 3.35 -> 3.70Improved
StackGAN versus GAN-INT-CLS on CUBStackGAN · CUBinception score: 2.88 -> 3.70Improved
StackGAN versus GAN-INT-CLS on Oxford-102StackGAN · Oxford-102inception score: 2.66 -> 3.20Improved
StackGAN versus GAWWN on CUBStackGAN · CUBinception score: 3.62 -> 3.70Improved
StackGAN versus GAN-INT-CLS on MS COCOStackGAN · MS COCOinception score: 7.88 -> 8.45Improved

Later papers that compared with this method

16 later accepted papers report StackGAN++ as a baseline in their results tables; 14 of them report a better number on most of the results they share with it.

8 more not listed.

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