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
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 changed | Where | Measured | Effect |
|---|---|---|---|
| add Mamba (LFF-SSM) and diffusion (CL-DM) modules to the backbone (ablation) | MPI-Mamba backbone · Real-world MPI data | PSNR: 20.202 -> 25.659 | Improved |
| add Mamba (LFF-SSM) and diffusion (CL-DM) modules to the backbone (ablation) | MPI-Mamba backbone · Real-world MPI data | SSIM: 0.531 -> 0.870 | Improved |
| add either Mamba module alone to the backbone (ablation) | MPI-Mamba backbone · Real-world MPI data | PSNR: better PSNR by 4.9 dB | Improved |
| add diffusion module alone to the backbone (ablation) | MPI-Mamba backbone · Real-world MPI data | PSNR: better PSNR by 4.9 dB | Improved |
| add real-world data (10%) to simulation training (ablation) | MPI-Mamba · Real-world MPI data | PSNR: 15.20 -> 24.63 | Improved |
| increase real-world data proportion from 10% to 100% (ablation) | MPI-Mamba · Real-world MPI data | PSNR: 24.63 -> 25.68 | Improved |
| increase real-world data proportion from 80% to 100% (ablation) | MPI-Mamba · Real-world MPI data | SSIM: 0.873 -> 0.870 | No clear effect |
| increase training patch size from 16 to 64 (ablation) | MPI-Mamba · Real-world MPI data | PSNR: 20.212 -> 25.659 | Improved |
| replace CNN methods with MPI-Mamba | MPI-Mamba vs CNN baselines · Real-world MPI data | PSNR: PSNR by 1.9-8.1 dB | Improved |
| use natural-image restorers NAFNet instead of MPI-specific designs | NAFNet · Real-world MPI data | PSNR: 17.4842 vs AEPNet 23.7242 | Hurt |
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.
- Restormer — Restormer: Efficient Transformer for High-Resolution Image Restoration (CVPR 2022) · better on 1 of 1 shared result
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
- SVRMamba: Slice-to-Volume Reconstruction from Multiple MRI Stacks with Slice Sequence Guided Mamba (AAAI 2025 · similarity 0.84)
- S³-Mamba: Small-Size-Sensitive Mamba for Lesion Segmentation (AAAI 2025 · similarity 0.83)
- MambaSCI: Efficient Mamba-UNet for Quad-Bayer Patterned Video Snapshot Compressive Imaging (NeurIPS 2024 · similarity 0.83)
- MobileMamba: Lightweight Multi-Receptive Visual Mamba Network (CVPR 2025 · similarity 0.82)
- LC-Mamba: Local and Continuous Mamba with Shifted Windows for Frame Interpolation (CVPR 2025 · similarity 0.82)
- DiMSUM: Diffusion Mamba - A Scalable and Unified Spatial-Frequency Method for Image Generation (NeurIPS 2024 · similarity 0.82)
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.
