AI Paper Atlas

Research map / Image generation / Autoregressive and latent generation

Image Inpainting Guided by Coherence Priors of Semantics and Textures

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

CVPR 2021 · Image generation › Autoregressive and latent generation · approach: Classical generative image synthesis · 119 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
Add SWAP to the joint multi-scale base method (ablation)Image inpainting on Outdoor Scenes · Outdoor ScenesPSNR: 17.43 -> 20.58Improved
Add SWAP to the joint multi-scale base method (ablation)Image inpainting on Outdoor Scenes · Outdoor ScenesFID: 57.31 -> 39.46Improved
Replace attention across all semantics with semantic-wise SWAP (ablation)Image inpainting on Outdoor Scenes · Outdoor ScenesPSNR: 19.77 -> 20.58Improved
Replace attention across all semantics with semantic-wise SWAP (ablation)Image inpainting on Outdoor Scenes · Outdoor ScenesFID: 43.54 -> 39.46Improved
Add coherence loss to the SWAP variant (ablation)Image inpainting on Outdoor Scenes · Outdoor ScenesPSNR: 20.58 -> 21.18Improved
Add coherence loss to the SWAP variant (ablation)Image inpainting on Outdoor Scenes · Outdoor ScenesFID: 39.46 -> 38.15Improved
Use semantic-wise attention and coherence losses rather than the base framework (ablation)Image inpainting on Outdoor Scenes · Outdoor ScenesSSIM: 0.65 -> 0.81Improved
Use the full coherence-prior method rather than SGE-NetImage inpainting on Cityscapes, centering holes · Cityscapes, centering holesSSIM: 0.85 -> 0.84Hurt
Use the full coherence-prior method rather than SGE-NetImage inpainting on Outdoor Scenes, centering holes · Outdoor Scenes, centering holesSSIM: 0.81 -> 0.81No clear effect
Jointly optimize inpainting and segmentation with the coherence-prior methodSemantic segmentation · Outdoor ScenesmIoU%: 0.68 -> 0.71Improved
Jointly optimize inpainting and segmentation with the coherence-prior methodSemantic segmentation · CityscapesmIoU%: 0.53 -> 0.57Improved

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