AI Paper Atlas

Research map / Image generation / Super-resolution

"Restore Globally, Refine Locally: A Mask-Guided Scheme to Accelerate Super-Resolution Networks"

Xiaotao Hu, Jun Xu, Shuhang Gu, Ming-Ming Cheng, Li Liu

ECCV 2022 · Image generation › Super-resolution · approach: CNN and transformer SR architectures · 15 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 two-channel softmax spatial feature in the MP module (ablation)PAN-M · Urban100 (x4)PSNR: 25.96 -> 26.02Improved
use the three-step training strategy instead of end-to-end (ablation)FSRCNN-M · Urban100 (x2)PSNR: 29.10 -> 29.56Improved
add supervision of the MP module with the coarse-final difference (ablation)FSRCNN-M · Urban100 (x2)PSNR: 29.50 -> 29.56Improved
select largest errors rather than random (ablation)RFDN-M · Urban100 (x2)PSNR: 32.14 -> 32.36Improved
select largest errors rather than smaller (ablation)RFDN-M · Urban100 (x2)PSNR: 32.03 -> 32.36Improved
refine more patches (K=All/2 instead of K=1000, largest errors) (ablation)RFDN-M · Urban100 (x2)PSNR: 32.26 -> 32.36Improved
give Refine-Net 2 blocks instead of 6 (14+2 vs 10+6) (ablation)PAN-M · Urban100 (x2)PSNR: 31.67 -> 31.90Improved
increase feature patch size p from 4 to 8 (ablation)FSRCNN-M · Urban100 (x4)PSNR: 24.50 -> 24.48Hurt
replace ClassSR with MGA accelerationRCAN · Urban100 (x4, RGB)PSNR: 25.14 -> 25.43Improved
replace ClassSR with MGA accelerationRCAN · Kirin 980 mobileinference time: 38.91s -> 35.51sImproved
apply MGA to decomposed networkRCAN-D · Urban100 (x4)FLOPs (G): 808.21 -> 728.52Improved
apply MGA to decomposed networkPAN-D · Urban100 (x4)FLOPs (G): 36.05 -> 29.74Improved

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