AI Paper Atlas

Research map / Image generation / Super-resolution

SRFormer: Permuted Self-Attention for Single Image Super-Resolution

Yupeng Zhou, Zhen Li, Chun-Le Guo, Song Bai, Ming-Ming Cheng, Qibin Hou

ICCV 2023 · Image generation › Super-resolution · approach: Efficient lightweight super-resolution · 423 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
enlarge window size from 12x12 to 24x24 (ablation)SRFormer · Urban100 (x2)PSNR (dB): 33.08 -> 33.51Improved
enlarge window size from 8x8 to 16x16 (ablation)SwinIR · Urban100 (x2)PSNR (dB): 33.09 -> 33.40Improved
enlarge window from 12x12 to 24x24 without ConvFFN (ablation)SRFormer w/o ConvFFN · Urban100 (x2)PSNR (dB): 32.99 -> 33.38Improved
add ConvFFN (5x5 depth-wise conv in FFN) (ablation)SRFormer 24x24 · Urban100 (x2)PSNR (dB): 33.38 -> 33.51Improved
add 5x5 depth-wise conv in ConvFFN (ablation)SRFormer · Manga109 (x2)PSNR (dB): 39.44 -> 39.49Improved
use 3x3 instead of no depth-wise conv (ablation)SRFormer · Manga109 (x2)PSNR (dB): 39.44 -> 39.34Hurt
use 5x5 instead of 3x3 depth-wise conv (ablation)SRFormer · Urban100 (x2)PSNR (dB): 33.42 -> 33.51Improved
replace token reduction with permuted self-attention (ablation)SRFormer (S=24) · Urban100 (x2)PSNR (dB): 33.24 -> 33.38Improved
replace random token sampling with permuted self-attention (ablation)SRFormer (S=24) · Urban100 (x2)PSNR (dB): 32.34 -> 33.38Improved
use PSA with 24x24 window instead of SwinIR 8x8 windowSRFormer · Urban100 (x2)parameters and MACs: 11.75M and 2868G -> 10.06M and 2703GImproved
replace SwinIR with SRFormer (DIV2K-trained)SRFormer · Urban100 (x2)PSNR (dB): 33.40 -> 33.86Improved
add self-ensemble (SRFormer+)SRFormer · Urban100 (x2, DF2K)PSNR (dB): 34.09 -> 34.29Improved

Later papers that compared with this method

4 later accepted papers report SRFormer as a baseline in their results tables; 3 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