AI Paper Atlas

Research map / Image generation / Autoregressive and latent generation

Free-Form Image Inpainting With Gated Convolution

Jiahui Yu, Zhe Lin, Jimei Yang, Xiaohui Shen, Xin Lu, Thomas S. Huang

ICCV 2019 · Image generation › Autoregressive and latent generation · approach: Classical generative image synthesis · 2,164 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
replace rule-based partial convolution with learnable gated convolutioninpainting network (same framework) · Places2 val (free-form mask)mean l1 error: 10.4% -> 9.1%Improved
replace rule-based partial convolution with learnable gated convolutioninpainting network (same framework) · Places2 val (free-form mask)mean l2 error: 1.9% -> 1.6%Improved
replace rule-based partial convolution with learnable gated convolutioninpainting network (same framework) · Places2 val (rectangular mask)mean l1 error: 9.8% -> 8.6%Improved
replace rule-based partial convolution with learnable gated convolutioninpainting network (same framework) · Places2 val (rectangular mask)mean l2 error: 2.3% -> 2.0%Improved
use gated-convolution network instead of reimplemented PartialConvinpainting network · Places2 user study naturalnessnaturalness rating (1-10): 7.07 -> 7.72Improved
use gated-convolution model instead of official PartialConv modelinpainting system · Places2 user study pairwisepreference (%): 79.4% vs. 20.6%Improved
use gated-convolution model instead of official PartialConv modelinpainting system · Places2 user study naturalnessnaturalness rating (1-10): 6.54 -> 7.72Improved
add SN-PatchGAN (spectral-normalized patch discriminator) instead of one global GAN without spectral normalization (ablation)gated convolution inpainting network · Places2 qualitative examplesvisual qualityImproved
add gated convolution to Global&Local-style rectangle-mask baselines on free-form masks (compare Ours vs Global&Local)inpainting network · Places2 val (free-form mask)mean l1 error: 21.6% -> 9.1%Improved
add extra pixel-wise loss on HED output features for sketch guidance (ablation)user-guided inpainting model · Places2 sketch-guided inpaintinginpainting qualityNo clear effect
slim model width by 25% after adding gated convolutions (ablation)gated convolution inpainting network · Places2performance: 25%No clear effect
add U-Net skip connections (ablation)encoder-decoder inpainting network · Places2 non-narrow masksinpainting qualityNo clear effect

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