AI Paper Atlas

Research map / Image generation / GANs

StackGAN++: Realistic Image Synthesis with Stacked Generative Adversarial Networks

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

TPAMI 2018 · Image generation › GANs · approach: Large-scale GAN latent analysis · 1,279 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 Conditioning Augmentation (ablation)StackGAN-v1 256x256 · CUBInception score: 3.31 -> 3.70Improved
add Conditioning Augmentation (ablation)Stage-I GAN 256x256 · CUBInception score: 2.48 -> 3.02Improved
add Conditioning Augmentation (ablation)Stage-I GAN 64x64 · CUBInception score: 2.66 -> 2.95Improved
add Stage-II refinement on top of Stage-I (ablation)StackGAN-v1 · CUBInception score: 3.02 -> 3.70Improved
feed text again at Stage-II (ablation)StackGAN-v1 256x256 · CUBInception score: 3.45 -> 3.70Improved
feed text again at Stage-II (ablation)StackGAN-v1 128x128 · CUBInception score: 3.13 -> 3.35Improved
increase output resolution from 128x128 to 256x256 (ablation)StackGAN-v1 · CUBInception score: 3.35 -> 3.70Improved
add intermediate multi-scale branches G1, G2 (ablation)StackGAN-v2 · CUBInception score: 3.49 -> 4.04Improved
add multi-scale branches versus all-256 branches (ablation)StackGAN-v2 · CUBInception score: 2.89 -> 4.04Improved
use multiple 256x256 discriminators with different initializations (ablation)StackGAN-v2-G3 · CUBInception score: 3.49 -> 3.22Hurt
add joint conditional and unconditional discriminator (JCU) (ablation)StackGAN-v2 · CUBInception score: 3.77 -> 4.04Improved
add color-consistency regularization (ablation)StackGAN-v2 · ImageNet-dogInception score: 9.02 -> 9.55Improved

Later papers that compared with this method

3 later accepted papers report StackGANv2 as a baseline in their results tables; 2 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