AI Paper Atlas

Research map / Image generation / GANs

Unsupervised Class-Specific Deblurring

Thekke Madam Nimisha, Kumar Sunil, A. N. Rajagopalan

ECCV 2018 · Image generation › GANs · approach: GAN-based image manipulation · 66 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 reblurring CNN module to GAN-only training (ablation)unsupervised GAN deblurrer · Face deblurring (qualitative, Fig. 3)visual qualityImproved
add scale-space gradient module on top of GAN plus reblur (ablation)unsupervised GAN deblurrer · Face deblurring (qualitative, Fig. 3)visual qualityImproved
use reblur-and-gradient self-guided GAN instead of CycleGANunsupervised deblurring · Face deblurring (synthetic, CelebA)PSNR (dB): 8.93 -> 22.80Improved
use reblur-and-gradient self-guided GAN instead of CycleGANunsupervised deblurring · Text deblurring (synthetic)PSNR (dB): 13.19 -> 23.22Improved
use reblur-and-gradient self-guided GAN instead of CycleGANunsupervised deblurring · Checkerboard deblurring (synthetic)PSNR (dB): 21.92 -> 20.61Hurt
unsupervised training instead of supervised Nah et al.deblurring network · Face deblurring (synthetic, CelebA)PSNR (dB): 24.12 -> 22.80Hurt
unsupervised training instead of supervised Nah et al.deblurring network · Text deblurring (synthetic)PSNR (dB): 18.72 -> 23.22Improved
unsupervised training instead of supervised text-specific Hradis et al.deblurring network · Text deblurring (synthetic)PSNR (dB): 24.28 -> 23.22Hurt
unsupervised training instead of supervised Hradis et al.deblurring network · Text deblurring (synthetic)CER: 0.0891 -> 0.126Hurt
use unsupervised network instead of conventional Pan et al. [30] text priordeblurring · Text human surveyuser preference: 97%Improved
use unsupervised network instead of supervised Hradis et al. [12]deblurring · Text human surveyuser preference: 43% vs 57%Hurt
use unsupervised network instead of exemplar-based Pan et al. [29] (with GT shown)face deblurring · Face human surveyuser preference: 81%Improved

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