AI Paper Atlas

Research map / Image generation / Autoregressive and latent generation

Generating Diverse Structure for Image Inpainting With Hierarchical VQ-VAE

Jialun Peng, Dong Liu, Songcen Xu, Houqiang Li

CVPR 2021 · Image generation › Autoregressive and latent generation · approach: Generative latent space tooling · 230 citations (OpenAlex)

Check 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
Use full attention rather than cross attention on learned features (ablation)Texture generator · CelebA-HQFID: 11.26 -> 11.55Improved
Use structural features instead of learned features for attention (ablation)Texture generator · CelebA-HQFID: 11.26 -> 10.12Improved
Use full attention on structural features (ablation)Texture generator · CelebA-HQFID: 11.55 -> 9.670Improved
Add structural feature loss (ablation)Texture generator · CelebA-HQSSIM: 0.8581 -> 0.8589Improved
Add textural feature loss (ablation)Texture generator · CelebA-HQFID: 11.02 -> 10.34Improved
Add both structural and textural feature losses (ablation)Texture generator · CelebA-HQFID: 11.02 -> 9.670Improved
Replace proposed feature losses with perceptual and style losses (ablation)Texture generator · CelebA-HQIS: 3.467 -> 3.388Hurt
Use Ours rather than PICMultiple-solution inpainting · CelebA-HQ testFID: 11.70 -> 9.784Improved
Use Ours rather than UCTGANMultiple-solution inpainting · CelebA-HQ testFID: 11.74 -> 9.784Improved
Use Ours rather than PICMultiple-solution inpainting · CelebA-HQ testLPIPS diversity: 0.029 vs 0.029No clear effect

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