AI Paper Atlas

Research map / Image generation / Super-resolution

ESSAformer: Efficient Transformer for Hyperspectral Image Super-resolution

Mingjin Zhang, Chi Zhang, Qiming Zhang, Jie Guo, Xinbo Gao, Jing Zhang

ICCV 2023 · Image generation › Super-resolution · approach: Efficient lightweight super-resolution · 189 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 multi-head self-attention with ESSA (ablation)ESSAformer · Chikusei 4xPSNR: 40.4310 -> 40.7648Improved
replace windowed Swin attention with ESSA (ablation)ESSAformer · Chikusei 4xPSNR: 40.1122 -> 40.7648Improved
increase Taylor order from 0 to 1 in the kernel mapping (ablation)ESSA · Chikusei 4xPSNR: 40.5474 -> 40.7648Improved
increase Taylor order beyond 1 (ablation)ESSA · Chikusei 4xPSNR: 40.7648 -> 40.8012 (order 3)No clear effect
increase stages from 3 to 5 (ablation)ESSAformer · Chikusei 4xPSNR: 40.42 -> 40.76Improved
increase stages from 5 to 7 or 9 (ablation)ESSAformer · Chikusei 4xPSNR: 40.7648 -> 40.7314 (7), 40.7191 (9)No clear effect
use SCC spectral correlation attention instead of MHSA (ablation)ESSAformer · Cave 4x (128x128 crops)PSNR: 44.5341 -> 44.9210Improved
kernelize SCC attention into ESSA for linear complexity (ablation)SCC attention · Chikusei 4x (128x128 crops)PSNR: 41.3273 -> 41.4177Improved
use ESSA instead of other linear attention (Performer, NPRF, linear) (ablation)ESSAformer · Chikusei 4xPSNR: 40.5833 -> 40.7648 (vs Performer)Improved
use ESSA instead of MHSA at larger input resolution (ablation)ESSAformer · FLOPs at 40x40 inputFLOPs: 1326.80 G -> 304.97 GImproved
use ESSAformer on large datasetsSwinIR · NTIRE2020PSNR: 34.9186 -> 34.8674No clear effect
increase scale factor from 2x to 8xESSAformer · PaviaPSNR: 38.7896 -> 27.1114Hurt

Later papers that compared with this method

2 later accepted papers report ESSAFormer as a baseline in their results tables; 2 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