atlas

Research map / Image generation / Image restoration

PD-GAN: Probabilistic Diverse GAN for Image Inpainting

CVPR 2021 · Image generation › Image restoration · approach: Priors for restoration networks · 238 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
Use PD-GAN instead of PICPlaces2 diverse inpainting · Places2LPIPS diversity, mask region: 0.1547 -> 0.1799Helped
Use PD-GAN instead of PICPlaces2 diverse inpainting · Places2LPIPS diversity, full image: 0.1096 -> 0.1238Helped
Add perceptual diversity loss (ablation)PD-GAN · Places2, mask 40-50%LPIPS diversity: 0.1934 -> 0.2206Helped
Add perceptual diversity loss (ablation)PD-GAN · Places2, mask 40-50%FID: 56.55 -> 52.68Helped
Replace conventional diversity loss with perceptual diversity loss (ablation)PD-GAN · Places2, mask 40-50%FID: 61.55 -> 52.68Helped
Replace conventional diversity loss with perceptual diversity loss (ablation)PD-GAN · Places2, mask 40-50%LPIPS diversity: 0.198 -> 0.2206Helped
Add hard SPDNorm alongside soft SPDNorm (ablation)PD-GAN · Places2, mask 40-50%FID: 61.22 -> 52.68Helped
Add soft SPDNorm alongside hard SPDNorm (ablation)PD-GAN · Places2, mask 40-50%FID: 61.48 -> 52.68Helped
Replace SPDNorm with SPADE (ablation)PD-GAN · Places2, mask 40-50%FID: 52.68 -> 60.55Hurt

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