AI Paper Atlas

Research map / Image generation / Super-resolution

SMFANet: A Lightweight Self-Modulation Feature Aggregation Network for Efficient Image Super-Resolution

mingjun zheng, Long Sun, Jiangxin Dong, Jinshan Pan

ECCV 2024 · Image generation › Super-resolution · approach: Efficient lightweight super-resolution · 127 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 SMFA module (ablation)SMFANet · Urban100 x4PSNR: 25.54 -> 26.19Improved
add EASA branch (ablation)SMFANet · Urban100 x4PSNR: 25.94 -> 26.19Improved
add LDE branch (ablation)SMFANet · Urban100 x4PSNR: 25.92 -> 26.19Improved
replace EASA with window-based self-attention (ablation)SMFANet · Urban100 x4PSNR: 26.19 -> 26.20No clear effect
replace EASA with window-based SA (efficiency) (ablation)SMFANet · x4 SRGPU memory (M): 93.20 -> 269.69Hurt
use parallel EASA and LDE branches instead of dual LDE or dual EASA (ablation)SMFANet · Urban100 x4PSNR: 26.02 / 25.94 -> 26.19Improved
run EASA and LDE in parallel rather than sequentially (ablation)SMFANet · Urban100 x4PSNR: 26.04 -> 26.19Improved
add variance modulation sigma^2(X) in EASA (ablation)SMFANet · Urban100 x4PSNR: 26.13 -> 26.19Improved
use addition instead of element-wise product for variance modulation (ablation)SMFANet · Urban100 x4PSNR: 26.14 -> 26.19Improved
add PCFN (ablation)SMFANet · Urban100 x4PSNR: 25.89 -> 26.19Improved
replace PCFN with GDFN (ablation)SMFANet · Urban100 x4PSNR: 26.19 -> 26.22No clear effect
train on DF2K instead of DIV2KSMFANet · Manga109 x4PSNR: 30.72 -> 30.82Improved

Later papers that compared with this method

1 later accepted paper reports SMFANet as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

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