AI Paper Atlas

Research map / Architectures and efficiency / Attention and transformers

Fast and Accurate Image Restoration with Rank Enhanced Linear Attention

Yuang Ai

ECCV 2026 · Architectures and efficiency › Attention and transformers · approach: Efficient image transformers

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 rank-enhancing depthwise conv (RELA) to vanilla linear attention (ablation)LAformer-T · SOTS-Indoor dehazingPSNR (dB): 39.28 -> 41.17 (+1.89 dB)Improved
use RELA instead of window self-attention (ablation)LAformer-T · SOTS-Indoor dehazingPSNR (dB): 40.76 -> 41.17Improved
use RELA instead of transposed self-attention (ablation)LAformer-T · SOTS-Indoor dehazingPSNR (dB): 40.52 -> 41.17Improved
add channel attention block (CAB) (ablation)LAformer-T · SOTS-Indoor dehazingPSNR (dB): 40.81 -> 41.17Improved
use CG-FFN instead of MLP (ablation)LAformer-T · SOTS-Indoor dehazingPSNR (dB): 40.20 -> 41.17Improved
add depthwise conv in CG-FFN (ablation)LAformer-T · SOTS-Indoor dehazingPSNR (dB): 40.11 -> 41.17Improved
add GLU gating in CG-FFN (ablation)LAformer-T · SOTS-Indoor dehazingPSNR (dB): 40.86 -> 41.17Improved
use 1+ELU instead of ReLU as activation in RELA (ablation)LAformer-B · GoPro motion deblurringPSNR (dB): 33.38 -> 33.40No clear effect
enlarge DWC kernel from 3x3 to 5x5 (ablation)LAformer-B · GoPro motion deblurringPSNR (dB): 33.35 -> 33.40Improved
enlarge DWC kernel from 5x5 to 7x7 (ablation)LAformer-B · GoPro motion deblurringPSNR (dB): 33.40 -> 33.41No clear effect
use LAformer instead of DiT-S/2 for diffusion generationDiT-S/2 · ImageNet 256 class-conditional diffusion (400K steps)FID: 68.40 -> 50.39Improved
use LAformer instead of DiT-XL/2 for diffusion generationDiT-XL/2 · ImageNet 256 class-conditional diffusion (400K steps)FID: 19.47 -> 11.31Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

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