AI Paper Atlas

Research map / Image generation / Text-to-image diffusion

ForCenNet: Foreground-Centric Network for Document Image Rectification

Peng Cai, Qiang Li, Kaicheng Yang, Dong Guo, Jia Li, Nan Zhou, Xiang An, Ninghua Yang, Jiankang Deng

ICCV 2025 · Image generation › Text-to-image diffusion · approach: Personalized and region-controlled generation · 1 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 mask-guided transformer decoder (ablation)ForCenNet · DocUNet (ablation)MS-SSIM: 0.558 -> 0.571Improved
add mask-guided transformer decoder (ablation)ForCenNet · DocUNet (ablation)LD: 5.44 -> 4.95Improved
add curvature consistency loss (ablation)ForCenNet · DocUNet (ablation)MS-SSIM: 0.565 -> 0.571Improved
add curvature consistency loss (ablation)ForCenNet · DocUNet (ablation)CER: 0.169 -> 0.141Improved
add both mask-guided decoder and curvature loss (ablation)ForCenNet · DocUNet (ablation)LD: 7.06 -> 4.95Improved
make foreground segmentation differentiable instead of frozen separately trained model (ablation)ForCenNet · DocUNet (ablation)MS-SSIM: 0.468 -> 0.571Improved
make foreground segmentation differentiable instead of frozen separately trained model (ablation)ForCenNet · DocUNet (ablation)CER: 0.212 -> 0.141Improved
scale distortion samples per image from x1 to x100 (ablation)ForCenNet · DocUNet (65 images)MS-SSIM: 0.449 -> 0.530Improved
scale distortion samples from x100 to x1000 (ablation)ForCenNet · DocUNet (65 images)MS-SSIM: 0.530 -> 0.571Improved
scale distortion samples from x1000 to x5000 (ablation)ForCenNet · DocUNet (65 images)MS-SSIM: 0.571 -> 0.569No clear effect
coarser line sampling interval 4 to 32 pixels (ablation)ForCenNet · DocUNetMS-SSIM: 0.582 -> 0.569Hurt
train on Doc3D undistorted images instead of DocUNet/DIR300 images (ablation)ForCenNet · DocUNetMS-SSIM: 0.582 -> 0.579Mixed

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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