AI Paper Atlas

Research map / Image generation / Super-resolution

WARP: Wide Attention with Rich Projections for Image Super-Resolution

Jiwon Kim, Kyoung Mu Lee

ECCV 2026 · Image generation › Super-resolution · approach: Perceptual and real-world SR · 0 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 nonlinear shared QKV projection instead of linear QKV (same depth) (ablation)WARP C=96 · Set5 x4 SRPSNR (dB): 32.18 -> 32.48Improved
Add nonlinear projection versus linear QKV with depth increased to L=9 (ablation)WARP C=96 · Set5 x4 SRPSNR (dB): 32.47 -> 32.48No clear effect
Share QKV projection across blocks instead of independent projections (ablation)WARP C=96 · Set5 x4 SRPSNR (dB): 32.41 -> 32.48Improved
Add channel attention branch to spatial-only attention (ablation)WARP C=96 · Set5 x4 SRPSNR (dB): 32.43 -> 32.48Improved
Add nonlinear projection instead of linear QKV with L=20 at full scale (ablation)WARP C=320 · Urban100 x4 SRPSNR (dB): 27.65 -> 27.81Improved
Add dual attention (L=12) instead of spatial-only with L=16 at full scale (ablation)WARP C=320 · Urban100 x4 SRPSNR (dB): 27.81 -> 27.95Hurt
Enlarge attention window from 16x16 to 64x64 (trained from scratch) (ablation)WARP C=320 · Urban100 x4 SRPSNR (dB): 26.84 -> 28.08Improved
Enlarge window from 16x16 to 64x64 on smooth Set5 (ablation)WARP C=320 · Set5 x4 SRPSNR (dB): 32.65 -> 33.13Improved
Use naive tile 128 extrapolation instead of training tile 64 (ablation)WARP x2 · Urban100 x2 SRPSNR (dB): 34.85 -> 34.72Hurt
Add standard YaRN temperature (tau~1.03) to naive extrapolation (ablation)WARP x2 · Urban100 x2 SRPSNR (dB): 34.72 -> 34.58Hurt
Use inverted temperature tau=0.80 instead of standard YaRN temperature (ablation)WARP x2 · Urban100 x2 SRPSNR (dB): 34.58 -> 34.95Improved
Add 50K iterations YaRN fine-tuning (ablation)WARP x2 · Urban100 x2 SRPSNR (dB): 34.95 -> 34.99Improved

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