AI Paper Atlas

Research map / Image generation / Image restoration

End-to-End Unsupervised Document Image Blind Denoising

Mehrdad J. Gangeh, Marcin Plata, Hamid R. Motahari Nezhad, Nigel P Duffy

ICCV 2021 · Image generation › Image restoration · approach: Self-supervised image denoising · 22 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 classifier C to the embedder (ablation)Proposed MoE cycle-GAN · Dataset I (watermarked scientific pages)PSNR: 37.99 -> 38.33Improved
add classifier C to the embedder (ablation)Proposed MoE cycle-GAN · Dataset I (watermarked scientific pages)Max deterioration (%): 14.73 -> 9.93Improved
add classifier C to the embedder (ablation)Proposed MoE cycle-GAN · Dataset I (watermarked scientific pages)Averaged deterioration (%): 2.54 -> 2.55No clear effect
add deep mixture of experts with embedder to cycle-GANcycle-GAN · Dataset I (watermarked scientific pages)Averaged deterioration (%): 7.85 -> 2.55Improved
add deep mixture of experts with embedder to cycle-GANcycle-GAN · Dataset I (watermarked scientific pages)PSNR: 36.52 -> 38.33Improved
add deep MoE to cycle-GANcycle-GAN · Dataset II (Tobacco800 noisy pages)Averaged OCR improvement (%): 5.94 -> 7.2Improved
add deep MoE to cycle-GANcycle-GAN · Dataset III (in-house noisy pages)Averaged OCR improvement (%): 6.30 -> 9.52Improved
replace sequential cycle-GAN training with unified MoE modelcycle-GAN (Sequential) · Dataset II (Tobacco800 noisy pages)Averaged OCR improvement (%): 6.03 -> 7.2Improved
replace sequential cycle-GAN training with unified MoE modelcycle-GAN (Sequential) · Dataset III (in-house noisy pages)Averaged OCR improvement (%): 7.10 -> 9.52Improved
use unsupervised unified model instead of supervised REDNetREDNet · Dataset I (watermarked scientific pages)Averaged deterioration (%): 1.84 -> 2.55Hurt
use unsupervised unified model instead of supervised DE-GANDE-GAN · Dataset I (watermarked scientific pages)Averaged deterioration (%): 3.74 -> 2.55Improved
clean pages with proposed model before OCRABBYY OCR · Dataset I (watermarked scientific pages)Averaged deterioration (%): 7.71 -> 2.55Improved

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