AI Paper Atlas

Research map / Image generation / Image restoration

MPI-Mamba: Latent Feature Fusion Mamba for Anisotropic Image Calibration and Deblurring in Magnetic Particle Imaging

Liwen Zhang, Zhaoji Miao, Yusong Shen, Zechen Wei, Hui Hui, Jie Tian

AAAI 2026 · Image generation › Image restoration · approach: Real-world restoration with unaligned data · 1 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 Mamba (LFF-SSM) and diffusion (CL-DM) modules to the backbone (ablation)MPI-Mamba backbone · Real-world MPI dataPSNR: 20.202 -> 25.659Improved
add Mamba (LFF-SSM) and diffusion (CL-DM) modules to the backbone (ablation)MPI-Mamba backbone · Real-world MPI dataSSIM: 0.531 -> 0.870Improved
add either Mamba module alone to the backbone (ablation)MPI-Mamba backbone · Real-world MPI dataPSNR: better PSNR by 4.9 dBImproved
add diffusion module alone to the backbone (ablation)MPI-Mamba backbone · Real-world MPI dataPSNR: better PSNR by 4.9 dBImproved
add real-world data (10%) to simulation training (ablation)MPI-Mamba · Real-world MPI dataPSNR: 15.20 -> 24.63Improved
increase real-world data proportion from 10% to 100% (ablation)MPI-Mamba · Real-world MPI dataPSNR: 24.63 -> 25.68Improved
increase real-world data proportion from 80% to 100% (ablation)MPI-Mamba · Real-world MPI dataSSIM: 0.873 -> 0.870No clear effect
increase training patch size from 16 to 64 (ablation)MPI-Mamba · Real-world MPI dataPSNR: 20.212 -> 25.659Improved
replace CNN methods with MPI-MambaMPI-Mamba vs CNN baselines · Real-world MPI dataPSNR: PSNR by 1.9-8.1 dBImproved
use natural-image restorers NAFNet instead of MPI-specific designsNAFNet · Real-world MPI dataPSNR: 17.4842 vs AEPNet 23.7242Hurt

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