AI Paper Atlas

Research map / Image generation / Super-resolution

Mutual Affine Network for Spatially Variant Kernel Estimation in Blind Image Super-Resolution

Jingyun Liang, Guolei Sun, Kai Zhang, Luc Van Gool, Radu Timofte

ICCV 2021 · Image generation › Super-resolution · approach: Blind super-resolution · 130 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
replace group convolution with MAConv (2 splits) (ablation)MANet · BSD100 x4 LR imagePSNR: 48.32 -> 49.39Improved
replace plain convolution with MAConv (2 splits) (ablation)MANet · BSD100 x4 LR imagePSNR: 48.85 -> 49.39Improved
increase MAConv channel splits from 2 to 4 (ablation)MANet · BSD100 x4 LR imagePSNR: 49.39 -> 49.77Improved
increase MAConv channel splits from 4 to 6 (ablation)MANet · BSD100 x4 LR imagePSNR: 49.77 -> 49.80No clear effect
increase channels from [32,64,32] to [128,256,128] (ablation)MANet with MAConv, 2 splits · BSD100 x4 LR imagePSNR: 45.87 -> 49.39Improved
use MAConv instead of group convolution at small width [32,64,32] (ablation)MANet · BSD100 x4 LR imagePSNR: 45.14 -> 45.87Improved
increase MAConv layers per residual block from 2 to 4 (receptive field 22x22 to 38x38) (ablation)MANet · toy spatially variant imagekernel accuracyHurt
train with kernel loss instead of LR image loss (ablation)MANet · toy spatially variant imagekernel estimationImproved
add Gaussian noise and JPEG compression to input (sigma 15, q 70 vs clean)MANet · BSD100 x4LR image PSNR: 45.45 -> 40.59Hurt
estimate spatially variant kernels with MANet instead of one kernel per image with IKCRRDB-SFT · BSD100 spatially variant type 2 (x4)PSNR: 26.03 -> 27.21Improved
estimate per-patch kernels with MANet instead of IKCRRDB-SFT · Urban100 spatially invariant (x4)PSNR: 25.16 -> 25.66Improved
MANet kernels under heavy noise vs IKCRRDB-SFT · BSD100 spatially variant type 1 (x4, noise 15)PSNR: 24.64 -> 24.89Improved

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