AI Paper Atlas

Research map / Image generation / Image restoration

Image Inpainting for Irregular Holes Using Partial Convolutions

Guilin Liu, Fitsum A. Reda, Kevin J. Shih, Ting-Chun Wang, Andrew Tao, Bryan Catanzaro

ECCV 2018 · Image generation › Image restoration · approach: Dehazing and deraining · 2,471 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 partial convolution with mask update instead of standard convolution (ablation)PConv U-Net inpainting · Irregular masks, hole ratio (0.2,0.3] no borderPSNR: 24.23 -> 24.54Improved
add partial convolution instead of standard convolution (ablation)PConv U-Net inpainting · Irregular masks, hole ratio (0.2,0.3] no borderL1 error (%): 2.20 -> 2.07Improved
add partial convolution instead of standard convolution (ablation)PConv U-Net inpainting · Irregular masks, hole ratio (0.2,0.3] no borderSSIM: 0.769 -> 0.775Improved
add partial convolution instead of standard convolution (ablation)PConv U-Net inpainting · Irregular masks, hole ratio (0.2,0.3] no borderInception score (lower is better): 0.603 -> 0.446Improved
add partial convolution instead of standard convolution (ablation)PConv U-Net inpainting · Irregular masks, hole ratio (0.5,0.6] no borderPSNR: 18.24 -> 18.21No clear effect
add partial convolution instead of standard convolution (ablation)PConv U-Net inpainting · Irregular masks, hole ratio (0.5,0.6] no borderL1 error (%): 6.66 -> 6.45Improved
add partial convolution instead of standard convolution (ablation)PConv U-Net inpainting · Irregular masks, hole ratio (0.01,0.1] no borderL1 error (%): 0.49 vs 0.52 (PConv 0.49 worse than PM 0.45)Hurt
add style loss terms (ablation)PConv U-Net inpainting · Qualitative inpaintingvisual artifactsImproved
use full style loss weight instead of a small weight (ablation)PConv U-Net inpainting · Qualitative inpaintingvisual artifactsImproved
add perceptual loss (ablation)PConv U-Net inpainting · Qualitative inpaintingvisual artifactsImproved
add total variation loss to reduce checkerboard artifacts (ablation)PConv U-Net inpainting · Qualitative inpaintingvisual artifactsNo 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