Skip to content

PaperCodex

Subscribe

Compositional Scene Modeling

GANformer: Compositional, Controllable Image Generation with Fewer Training Steps

GANformer: Compositional, Controllable Image Generation with Fewer Training Steps 1342

Traditional generative adversarial networks (GANs) often act as “black boxes”—they produce compelling images but offer little insight into how those…

12/27/2025Compositional Scene Modeling, Image Generation, Layout-to-image Synthesis
Copyright © 2026 PaperCodex.
  • Facebook
  • YouTube
  • Twitter

PaperCodex