AI Paper Atlas

Research map / Image generation / Autoregressive and latent generation

Guidance and Evaluation: Semantic-Aware Image Inpainting for Mixed Scenes

Liang Liao, Jing Xiao, Zheng Wang, Chia-Wen Lin, Shin’ichi Satoh

ECCV 2020 · Image generation › Autoregressive and latent generation · approach: Classical generative image synthesis · 140 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 SGIM (semantic-guided inference module) to Basic-Net (ablation)Basic-Net · Outdoor Scenes (centering holes)PSNR: 19.14 -> 19.58Improved
add SGIM (semantic-guided inference module) to Basic-Net (ablation)Basic-Net · Outdoor Scenes (centering holes)SSIM: 0.71 -> 0.77Improved
add SGIM (semantic-guided inference module) to Basic-Net (ablation)Basic-Net · Outdoor Scenes (centering holes)FID: 43.43 -> 41.49Improved
add SCEM (segmentation confidence evaluation) to SG-Net (ablation)SG-Net · Outdoor Scenes (centering holes)PSNR: 19.58 -> 20.53Improved
add SCEM (segmentation confidence evaluation) to SG-Net (ablation)SG-Net · Outdoor Scenes (centering holes)SSIM: 0.77 -> 0.81Improved
add SCEM (segmentation confidence evaluation) to SG-Net (ablation)SG-Net · Outdoor Scenes (centering holes)FID: 41.49 -> 40.67Improved
add SCEM to SG-NetSG-Net · Outdoor Scenes (irregular holes)FID: 41.74 -> 42.47Hurt
add SCEM to SG-NetSG-Net · Cityscapes (irregular holes)SSIM: 0.64 -> 0.75Improved
add SCEM to SG-NetSG-Net · Cityscapes (centering holes)PSNR: 23.04 -> 23.41Improved
semantic guidance via segmentation-map-conditioned inference (SG-Net) instead of edge-guided two-stage ECEC · Outdoor Scenes (irregular holes)SSIM: 0.83 -> 0.81Hurt
replace human-annotated segmentation labels with predicted labels from DPN/Deeplab v3+ for training SGE-Net (ablation)SGE-Net · Outdoor Scenes and Cityscapesinpainting qualityNo clear effect
use SGE-Net over SPG in a user preference studySPG · User study (80 images)preference rate (%): 73.2Improved

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