AI Paper Atlas

Research map / Detection and segmentation / CNN features

Unbiased Multi-Modality Guidance for Image Inpainting

Yongsheng Yu, Dawei Du, Libo Zhang, Tiejian Luo

ECCV 2022 · Detection and segmentation › CNN features · approach: Local features and context in CNNs · 26 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 edge and segmentation auxiliary branches (ablation)Multi-modality guided inpainting transformer · CelebA-HQ 128x128 center maskPSNR: 25.88 -> 26.70Improved
add edge and segmentation auxiliary branches (ablation)Multi-modality guided inpainting transformer · CelebA-HQ 128x128 center maskFID: 12.36 -> 11.40Improved
add segmentation branch on top of edge branch (ablation)Multi-modality guided inpainting transformer · CelebA-HQ 128x128 center maskPSNR: 26.19 -> 26.70Improved
add edge branch on top of segmentation branch (ablation)Multi-modality guided inpainting transformer · CelebA-HQ 128x128 center maskPSNR: 26.47 -> 26.70Improved
drop biased prior guidance from predicted auxiliary structures (MMT-4 to MMT-9) (ablation)Multi-modality guided inpainting transformer · CelebA-HQ 128x128 center maskFID: 12.59 -> 11.40Improved
replace concat with unbiased MSSA+ADN (MMT-1 to MMT-9) (ablation)Multi-modality guided inpainting transformer · CelebA-HQ 128x128 center maskFID: 20.01 -> 11.40Improved
use MSSA fusion instead of element-wise addition (ablation)Multi-modality guided inpainting transformer · CelebA-HQ 128x128 center maskFID: 12.64 -> 11.40Improved
use MSSA fusion instead of conv fusion (ablation)Multi-modality guided inpainting transformer · CelebA-HQ 128x128 center maskFID: 11.90 -> 11.40Improved
use ADN instead of AdaIN within MSSA (ablation)Multi-modality guided inpainting transformer · CelebA-HQ 128x128 center maskFID: 12.81 -> 11.40Improved
use ADN instead of SPADE within MSSA (ablation)Multi-modality guided inpainting transformer · CelebA-HQ 128x128 center maskFID: 12.17 -> 11.40Improved
increase ACB layers from 2 to 8 (ablation)Multi-modality guided inpainting transformer · CelebA-HQ 128x128 center maskFID: 12.18 -> 11.40Improved
quadruple channels in AOT blocks (dagger AOT@8) (ablation)Multi-modality guided inpainting transformer · CelebA-HQ 128x128 center maskFID: 11.61 -> 14.17Hurt

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