AI Paper Atlas

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

Foreground and Text-lines Aware Document Image Rectification

Heng Li, Xiangping Wu, Qingcai Chen, Qianjin Xiang

ICCV 2023 · Image generation › Text-to-image diffusion · approach: Personalized and region-controlled generation · 21 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
use both foreground and text-line attention modules instead of one (ablation)document rectification transformer · DocUNet BenchmarkMS-SSIM: 0.4785 -> 0.4978Improved
use both attention modules instead of one (ablation)document rectification transformer · DocUNet BenchmarkCER: 0.1889 -> 0.1705Improved
use both attention modules instead of one (ablation)document rectification transformer · DocUNet BenchmarkED: 748.46 -> 697.52Improved
compare proposed method with DocGeoNet on OCROurs vs DocGeoNet · DocUNet BenchmarkCER: 0.1821 -> 0.1705Improved
compare proposed method with DocGeoNet on OCROurs vs DocGeoNet · DIR300ED: 664.96 -> 652.80Improved
compare proposed method with DocGeoNet on image-distortion metricsOurs vs DocGeoNet · DIR300MS-SSIM: 0.6380 -> 0.6070Hurt
higher text content ratio in imageproposed method · DocUNet BenchmarkLD: 10.74 -> 6.34 (LD, low to high text ratio); MS-SSIM 0.54 -> 0.44Mixed

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