AI Paper Atlas

Research map / Image generation / GANs

Generative Adversarial Diffusion

U-Chae Jun, Jaeeun Ko, Jiwoo Kang

ICCV 2025 · Image generation › GANs · approach: Stabilized GAN training · 1 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 GAD adversarial regularizerStable diffusion · COCO2014 val text-to-imageFID: 13.52 -> 9.68Improved
add GAD adversarial regularizerStable diffusion · COCO2014 val text-to-imageCLIP score: 0.3143 -> 0.3471Improved
add GAD adversarial regularizerGLIGEN · GLIGEN bounding-box (CC3M 2K pairs)FID: 12.26 -> 9.12Improved
add GAD adversarial regularizerGLIGEN · GLIGEN bounding-box (CC3M 2K pairs)CLIP score: 0.292 -> 0.311Improved
add GAD adversarial regularizerTextual Inversion · Textual Inversion (GSO, 6 images)FID: 13.74 -> 8.71Improved
add GAD adversarial regularizerTextual Inversion · Textual Inversion (GSO, 6 images)CLIP similarity: 0.712 -> 0.764Improved
add GAD adversarial regularizerSyncDreamer · Novel view synthesis (GSO and Omni3D, 50 objects)PSNR: 20.25 -> 22.81Improved
add GAD adversarial regularizerSyncDreamer · Novel view synthesis (GSO and Omni3D, 50 objects)SSIM: 0.798 -> 0.858Improved
add GAD adversarial regularizerSyncDreamer · Novel view synthesis (GSO and Omni3D, 50 objects)LPIPS: 0.146 -> 0.119Improved
add GAD adversarial regularizerEra3D · Novel view synthesis (GSO and Omni3D, 50 objects)PSNR: 22.74 -> 24.12Improved
add GAD adversarial regularizerEra3D · Novel view synthesis (GSO and Omni3D, 50 objects)SSIM: 0.837 -> 0.891Improved
add GAD adversarial regularizerEra3D · Novel view synthesis (GSO and Omni3D, 50 objects)LPIPS: 0.126 -> 0.102Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

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