AI Paper Atlas

Research map / Image generation / Image restoration

Reverse Convolution and Its Applications to Image Restoration

Xuhong Huang, Shiqi Liu, Kai Zhang, Ying Tai, Jian Yang, Hui Zeng, Lei Zhang

ICCV 2025 · Image generation › Image restoration · approach: Priors for restoration networks · 17 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
use Gaussian+Softmax kernel init instead of Gaussian (ablation)Converse-DnCNN · Set12PSNR (dB): 30.60 -> 30.70Improved
use Gaussian instead of uniform kernel init (ablation)Converse-DnCNN · Set12PSNR (dB): 30.31 -> 30.60Improved
use 5x5 kernel instead of 3x3 (ablation)Converse-DnCNN · Set12PSNR (dB): 30.58 -> 30.70Improved
use 7x7 kernel instead of 5x5 (ablation)Converse-DnCNN · Set12PSNR (dB): 30.70 -> 30.71No clear effect
use circular padding instead of zero padding (ablation)Converse-DnCNN · Set12PSNR (dB): 30.63 -> 30.70Improved
use padding size 4 instead of 0 (ablation)Converse-DnCNN · Set12PSNR (dB): 30.67 -> 30.70No clear effect
initialize X0 with Y instead of zeros (ablation)Converse-DnCNN · Set12PSNR (dB): 30.66 -> 30.70Improved
initialize X0 with Interp(Y,s) instead of zeros (ablation)Converse-SRResNet · Set5 (x4 SR)PSNR (dB): 32.22 -> 32.25Improved
replace depthwise convolution with Converse2DConverse-DnCNN · Set12PSNR (dB): 30.64 -> 30.70Improved
replace depthwise transposed convolution with Converse2DConverse-DnCNN · BSD68PSNR (dB): 29.29 -> 29.36Improved
replace depthwise convolution with Converse2DSRResNet · Urban100 (x4 SR)PSNR (dB): 26.24 -> 26.24No clear effect
replace depthwise transposed convolution with Converse2DSRResNet · Urban100 (x4 SR)PSNR (dB): 25.89 -> 26.24Improved

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