AI Paper Atlas

Research map / Image generation / Image restoration

Deep Variational Network Toward Blind Image Restoration

Zongsheng Yue, Hongwei Yong, Qian Zhao, Lei Zhang, Deyu Meng, Kenneth K. Wong

TPAMI 2024 · Image generation › Image restoration · approach: Priors for restoration networks · 38 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
condition image posterior on noise variance (ablation)Baseline1 (q(z|y)) · DIV2K100 SR x4 (noise 2.55)PSNR (dB): 27.69 -> 27.71No clear effect
condition image posterior on blur kernel parameters (ablation)Baseline1 (q(z|y)) · DIV2K100 SR x4 (noise 2.55)PSNR (dB): 27.69 -> 27.86Improved
condition image posterior on both noise and kernel (ablation)Baseline3 (kernel only) · DIV2K100 SR x4 (noise 2.55)LPIPS (lower is better): 0.3611 -> 0.3588Improved
condition image posterior on noise, in addition to kernel (ablation)Baseline2 (noise only) · DIV2K100 SR x4 (noise 2.55)PSNR (dB): 27.71 -> 27.86Improved
use VIRNet estimated noise level instead of ground truth as FFDNet inputFFDNet · CBSD68 AWGN (sigma=50)PSNR (dB): 27.95 -> 27.92No clear effect
use VIRNet estimated noise level instead of ground truth as FFDNet inputFFDNet · CBSD68 AWGN (sigma=15)PSNR (dB): 33.87 -> 33.87No clear effect
use VIRNet estimated noise map instead of ground truth as FFDNet inputFFDNet · CBSD68 non-i.i.d. noise (Case 1)PSNR (dB): 28.79 -> 28.75No clear effect
use VIRNet estimated kernel instead of KernelGAN with USRNetUSRNet · DIV2K20 SR x4PSNR (dB): 14.52 -> 28.53Improved
use VIRNet estimated kernel instead of BSRDM with USRNetUSRNet · DIV2K20 SR x4PSNR (dB): 27.07 -> 28.53Improved
use VIRNet kernel instead of ground-truth kernel with USRNetUSRNet · DIV2K20 SR x4PSNR (dB): 29.19 -> 28.53Hurt
use blind VIRNet instead of non-blind DRUNetDRUNet · CBSD68 non-i.i.d. noise (Case 2)PSNR (dB): 28.64 -> 28.93Improved
use blind VIRNet instead of MPRNetMPRNet · SIDD real-world denoisingPSNR (dB): 39.62 -> 39.63No clear effect

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