atlas

Research map / Image generation / GANs

Constrained Generative Adversarial Networks for Interactive Image Generation

CVPR 2019 · Image generation › GANs · approach: Large-scale GAN latent analysis · 18 citations (OpenAlex)

Check your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's title only (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 relative-constraint conditioning and constraint-critic training to WGANWGAN · MNISTmean constraint satisfaction errorHelped
Increase the input set from 1 to 10 constraints (ablation)CONGAN · MNISTmean constraint satisfaction error: 0.0931 -> 0.0733Helped
Add CONGAN constraint conditioning and training to WGANWGAN · CelebAimage quality by discriminator score: 20.31 (WGAN generator) versus 18.32–20.00 (CONGAN generator)No clear effect
Add CONGAN constraint conditioning and training to WGANWGAN · Zappos50Kimage quality by discriminator score: 60.31 -> 5.43Hurt
Increase the input set from 1 to 10 constraints (ablation)CONGAN · CelebAmean constraint satisfaction error: 0.0885 -> 0.1325Hurt
Increase the input set from 1 to 10 constraints (ablation)CONGAN · Zappos50Kmean constraint satisfaction error: 0.0950 -> 0.1066Hurt
Balance constraint sampling over color bins instead of sampling only uniformly over imagesCONGAN · Zappos50Kconstraint satisfactionHelped

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