AI Paper Atlas

Research map / Image generation / Image restoration

Denoising Prior Driven Deep Neural Network for Image Restoration

Weisheng Dong, Peiyao Wang, Wotao Yin, Guangming Shi, Fangfang Wu, Xiaotong Lu

TPAMI 2018 · Image generation › Image restoration · approach: Priors for restoration networks · 533 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 degradation-model (back-projection) layers to the denoising network (ablation)DPDNN · Set10 deblurring (motion kernel 2, sigma_n=2.55)PSNR (dB): 32.22 -> 32.64Improved
add degradation-model layers to the denoising network (ablation)DPDNN · Urban100 SR (bicubic x3)PSNR (dB): 26.98 -> 27.61Improved
add degradation-model layers to the denoising network (ablation)DPDNN · Set10 deblurring and SRPSNR (dB): up to 0.42 dB and 0.63 dBImproved
initialize degradation layers with matrix A instead of random (ablation)DPDNN · Set10 deblurring (Kernel 1, noise 2.55)PSNR (dB): 33.19 -> 33.24No clear effect
initialize degradation layers with matrix A instead of random (ablation)DPDNN · Set14 SR (Gaussian x3)PSNR (dB): 29.88 -> 29.91No clear effect
pretrain the denoiser instead of random init (ablation)DPDNN · Set12 denoising (sigma=15)PSNR (dB): 32.91 -> 32.86No clear effect
pretrain the denoiser instead of random init (ablation)DPDNN · BSD68 denoising (sigma=50)PSNR (dB): 27.02 -> 27.03No clear effect
pretrain the denoiser instead of random init (ablation)DPDNN · BSD100 SR (bicubic x3)PSNR (dB): 29.00 -> 28.91No clear effect
use DPDNN instead of MemNetdenoising network · BSD68 denoising (sigma=50)PSNR (dB): 26.37 -> 27.02Improved
use DPDNN instead of DD-CNN at higher noise motion blurdeblurring · Set10 deblurring (motion kernel 1, sigma_n=7.65)PSNR (dB): 29.17 -> 29.01Hurt
use DPDNN instead of MemNetSR · Set5 SR (bicubic x3)PSNR (dB): 34.09 -> 33.93Hurt
use DPDNN instead of MemNet (fewer parameters)network complexity · BSD68 sigma=50run time (s/image): 0.278 -> 0.161Improved

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