AI Paper Atlas

Research map / 3D vision / Face and shape

DewarpNet: Single-Image Document Unwarping With Stacked 3D and 2D Regression Networks

Sagnik Das, Ke Ma, Zhixin Shu, Dimitris Samaras, Roy Shilkrot

ICCV 2019 · 3D vision › Face and shape · approach: Single-view 3D reconstruction · 95 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 CoordConv to texture mapping network (ablation)DewarpNet · Doc3D validationl2 error on B: 4.73 × 10−5 -> 3.99 × 10−5Improved
add CoordConv to texture mapping network (ablation)DewarpNet · Doc3D validationSSIM on D: 0.9260 -> 0.9281Improved
add LD loss to LB (ablation)DewarpNet · Doc3D validationl2 error on B: 1.40 × 10−4 -> 3.99 × 10−5Improved
add LD loss to LB (ablation)DewarpNet · Doc3D validationSSIM on D: 0.8539 -> 0.9281Improved
train DocUNet on Doc3D instead of its 2D synthetic datasetDocUNet · DocUNet benchmarkLocal Distortion: 14.08 -> 10.85Improved
train DocUNet on Doc3D instead of its 2D synthetic datasetDocUNet · DocUNet benchmarkMS-SSIM: 0.41 -> 0.4389Improved
use DewarpNet (3D shape then texture mapping) instead of DocUNet on Doc3DDewarpNet · DocUNet benchmarkLocal Distortion: 10.90 -> 8.98Improved
add refinement (shading removal) network to DewarpNetDewarpNet · DocUNet benchmarkMS-SSIM: 0.4692 -> 0.4735Improved
add refinement (shading removal) network to DewarpNetDewarpNet · DocUNet benchmarkLocal Distortion: 8.98 -> 8.95No clear effect
add refinement network to DewarpNetDewarpNet · OCR (25 images)CER: 0.3136 -> 0.2692Improved
use DewarpNet instead of DocUNetDewarpNet · OCR (25 images)CER: 0.4656 -> 0.3136Improved
use DewarpNet on the most challenging class (f) instead of DocUNetDewarpNet · DocUNet benchmark class (f)MS-SSIM and LDNo clear effect

Later papers that compared with this method

2 later accepted papers report DewarpNet as a baseline in their results tables; 2 of them report a better number on most of the results they share with it.

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