AI Paper Atlas

Research map / Image generation / Image restoration

Blur-Invariant Deep Learning for Blind-Deblurring

T. M. Nimisha, Akash Kumar Singh, A. N. Rajagopalan

ICCV 2017 · Image generation › Image restoration · approach: Image deblurring · 141 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 residual (ResNet) blocks to the denoising autoencoder (ablation)Encoder-decoder module · Autoencoder reconstruction of noisy image (Fig. 4)PSNR (dB): 23.1 dB -> 29.5 dBImproved
train GAN on autoencoder feature space instead of regressing clean pixels directly (ablation)Blur-invariant GAN generator · Qualitative blind deblurring (Fig. 5)qualitative output qualityImproved
add gradient loss to the MSE loss for autoencoder training (ablation)Autoencoder · Autoencoder trainingedge preservationImproved
use l1 instead of l2 loss for feature back-propagationGAN feature loss · GAN trainingtraining behaviorImproved
replace iterative prior-based deblurring with feed-forward network on GPUOurs vs Xu [37] · Run time, average image 1024x700run time: 34 sec -> 3.4 secImproved
compare against dark channel prior method on PSNROurs vs Pan [23] · Dataset of [29] (80 images, 8 kernels)PSNR (dB): 31.16 -> 30.54Hurt

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