AI Paper Atlas

Research map / Image generation / Super-resolution

Dynamic High-Pass Filtering and Multi-Spectral Attention for Image Super-Resolution

Salma Abdel Magid, Yulun Zhang, Donglai Wei, Won-Dong Jang, Zudi Lin, Yun Fu, Hanspeter Pfister

ICCV 2021 · Image generation › Super-resolution · approach: CNN and transformer SR architectures · 132 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 8 frequency components instead of 1 in channel attention (ablation)MMCA · Urban100 x4PSNR (dB): 26.24 -> 26.39Improved
use 16 instead of 8 frequency components (ablation)MMCA · Urban100 x4PSNR (dB): 26.39 -> 26.33No clear effect
use 2 frequency components instead of 1 (ablation)MMCA · Urban100 x4PSNR (dB): 26.24 -> 26.36Improved
add one HPF layer to the residual block (ablation)RCAN residual block · Manga109 x4PSNR (dB): 30.65 -> 30.82Improved
add a second HPF layer after the second convolution (ablation)RCAN residual block · Manga109 x4PSNR (dB): 30.82 -> 30.74Hurt
use 16 HPF groups instead of 2 (ablation)HPF module · Manga109 x4PSNR (dB): 30.82 -> 30.88Improved
use 4 HPF groups instead of 2 (ablation)HPF module · Manga109 x4PSNR (dB): 30.82 -> 30.79No clear effect
use 8 HPF groups instead of 2 (ablation)HPF module · Manga109 x4PSNR (dB): 30.82 -> 30.82No clear effect
replace SENet with MMCA channel attention (ablation)RCAN · Urban100 x4PSNR (dB): 26.24 -> 26.39Improved
replace FcaNet with MMCA channel attention (ablation)RCAN · Urban100 x4PSNR (dB): 26.29 -> 26.39Improved
replace SENet with MMCA channel attention (ablation)RCAN · Manga109 x4PSNR (dB): 30.65 -> 30.77Improved
replace FcaNet with MMCA channel attention (ablation)RCAN · Manga109 x4PSNR (dB): 30.67 -> 30.77Improved

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