AI Paper Atlas

Research map / 3D vision / Face and shape

Geometric Representation Learning for Document Image Rectification

Hao Feng, Wengang Zhou, Jiajun Deng, Yuechen Wang, Houqiang Li

ECCV 2022 · 3D vision › Face and shape · approach: Primitive-based shape abstraction · 47 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 structure encoder and textline extractor without supervision (ablation)DocGeoNet baseline · DocUNet BenchmarkLD: 8.11 -> 7.99Improved
add 3D shape supervision (ablation)DocGeoNet baseline · DocUNet BenchmarkLD: 7.99 -> 7.83Improved
add textline supervision (ablation)DocGeoNet baseline · DocUNet BenchmarkLD: 7.99 -> 7.79Improved
add both 3D shape and textline supervision (ablation)DocGeoNet baseline · DocUNet BenchmarkLD: 7.99 -> 7.71Improved
add both supervisions (ablation)DocGeoNet baseline · DocUNet BenchmarkCER: 0.2031 -> 0.1821Improved
add the preprocessing module (ablation)DocGeoNet · DocUNet BenchmarkLD: 8.61 -> 7.71Improved
add the preprocessing module (ablation)DocGeoNet · DocUNet BenchmarkMS-SSIM: 0.4843 -> 0.5040Improved
use learnable upsampling instead of bilinear (ablation)DocGeoNet · DocUNet BenchmarkLD: 7.77 -> 7.71Improved
use learnable upsampling instead of bilinear (ablation)DocGeoNet · DocUNet BenchmarkMS-SSIM: 0.5062 -> 0.5040No clear effect
compare DocGeoNet with DocTrDocTr · DIR300 testLD: 7.21 -> 6.40Improved

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