AI Paper Atlas

Research map / Image generation / Image restoration

MB-TaylorFormer V2: Improved Multi-Branch Linear Transformer Expanded by Taylor Formula for Image Restoration

Zhi Juan Jin, Yuwei Qiu, Kaihao Zhang, Hongdong Li, Wenhan Luo

TPAMI 2025 · Image generation › Image restoration · approach: Priors for restoration networks · 329 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 convolutional positional encoding (CPE) (ablation)MB-TaylorFormer-B V2 · ITS dehazingPSNR: 39.76 -> 41.00Improved
use CPE instead of MSAR (ablation)MB-TaylorFormer-B V2 · ITS dehazingPSNR: 40.73 -> 41.00Improved
use T-MSA++ instead of MDTA channel attention (ablation)MB-TaylorFormer-B V2 · ITS dehazingPSNR: 38.57 -> 41.00Improved
use T-MSA++ instead of Swin window attention (ablation)MB-TaylorFormer-B V2 · ITS dehazingPSNR: 36.59 -> 41.00Improved
use T-MSA++ instead of Flatten attention (ablation)MB-TaylorFormer-B V2 · ITS dehazingPSNR: 40.47 -> 41.00Improved
add parallel branches with single-scale conv patch embedding (Conv-P) (ablation)MB-TaylorFormer-B V2 · ITS dehazingPSNR: 39.43 -> 39.87Improved
replace standard conv with DSDCN in serial-parallel patch embedding (ablation)MB-TaylorFormer-B V2 · ITS dehazingPSNR: 40.25 -> 41.00Improved
truncate DSDCN offsets to [-3, 3] (ablation)MB-TaylorFormer-B V2 · ITS dehazingPSNR: 40.13 -> 41.00Improved
widen offset truncation range to [-4, 4] (ablation)MB-TaylorFormer-B V2 · ITS dehazingPSNR: 41.00 -> 40.53Hurt
vary focused factor p from 3 to 8 (ablation)MB-TaylorFormer-B V2 · ITS dehazingPSNR: 40.81, 41.00, 40.93, 40.76No clear effect
add second-order Taylor remainder approximation to Swin (ablation)Swin attention · ITS dehazingPSNR: 36.59 -> 36.50No clear effect
upgrade V1 to V2 (T-MSA++ and CPE)MB-TaylorFormer-L · deraining (average)PSNR: 33.66 -> 34.00Improved

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