AI Paper Atlas

Research map / Image generation / Image restoration

Revisiting Document Image Dewarping by Grid Regularization

Xiangwei Jiang, Rujiao Long, Nan Xue, Zhibo Yang, Cong Yao, Gui-Song Xia

CVPR 2022 · Image generation › Image restoration · approach: Dehazing and deraining · 39 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
use grid regularization with text-line and boundary constraints instead of learned dense deformationDocument dewarping · DocUNet benchmarkCER: 0.3001 (0.14) -> 0.2068 (0.141)Improved
use grid regularization with text-line and boundary constraints instead of learned dense deformationDocument dewarping · DocUNet benchmarkED: 1288.60 -> 896.48Improved
use grid regularization with text-line and boundary constraints instead of learned dense deformationDocument dewarping · DocUNet benchmarkMS-SSIM: 0.4879 -> 0.4922Improved
use grid regularization with text-line and boundary constraints instead of learned dense deformationDocument dewarping · DocUNet benchmarkLD: 8.50 -> 9.36Mixed
add text-line constraints to boundary constraints (ablation)Grid regularization dewarping · DocUNet benchmarkCER: 0.3511 (0.183) -> 0.2081 (0.142)Improved
add text-line constraints to boundary constraints (ablation)Grid regularization dewarping · DocUNet benchmarkED: 1513.04 -> 908.84Improved
add vertical-line constraints to boundary and text-line constraints (ablation)Grid regularization dewarping · DocUNet benchmarkCER: 0.2081 (0.142) -> 0.2068 (0.141)Improved
add vertical-line constraints to boundary and text-line constraints (ablation)Grid regularization dewarping · DocUNet benchmarkED: 908.84 -> 896.48Improved
replace proposed grid regularization with TFI, using the same boundary points (ablation)Grid regularization dewarping · DocUNet benchmarkCER: 0.3511 (0.183) -> 0.3379 (0.165)Hurt
replace proposed grid regularization with TPS, using the same boundary points (ablation)Grid regularization dewarping · DocUNet benchmarkED: 1513.04 -> 1457.30Improved

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