SwinMSI Weights
Trained checkpoints for the paper "SwinMSI: Window-Attention Super-Resolution Exploiting Long-Range Self-Similarity for Mass Spectrometry Imaging."
Source du modèle
- Type
- Other
- Taille du fichier
- 156–617 MB
- Version
- vBbdm
- Mis à jour
- 9 oct. 2026
- Source
- Hugging Face
Description de la source
SwinMSI — Trained Model Weights
Trained checkpoints for the paper "SwinMSI: Window-Attention Super-Resolution Exploiting Long-Range Self-Similarity for Mass Spectrometry Imaging."
SwinMSI reconstructs a full high-resolution MSI dataset (all m/z channels) from a single fast, low-resolution acquisition, so that high spatial resolution can be traded for far shorter acquisition time (≈7–8× in our DESI experiments). Its Swin-Transformer (window-attention) backbone exploits the long-range self-similarity of MSI ion images to recover fine detail, operating on the MSI data alone (no co-registered optical modality).
- 💻 Code: https://github.com/zhihaozhao98/SwinMSI
- 📊 Dataset (self-acquired DESI-MSI): https://huggingface.co/datasets/ZhihaoZhao/MSI-SuperRes-DESI
Files
| File | Method | Params | Size | Notes |
|---|---|---|---|---|
swinmsi_best.pth | SwinMSI (proposed) | 11.9 M | ~156 MB | SwinIR backbone, single Charbonnier loss, parameter-free pixel-space residual connection; 300 epochs @ 1e-4 then 100 epochs @ 1e-5 |
unet.pth | U-Net baseline | 31.2 M | ~357 MB | Convolutional encoder–decoder, identical training protocol |
bbdm.pth | BBDM (Brownian-bridge diffusion) | ~78 M | ~607 MB | 1000-step training, 250-step DDIM sampling at inference |
ldm.pth | LDM (latent diffusion) | ~81 M | ~617 MB | VAE + conditional latent diffusion U-Net |
The interpolation baselines (bilinear, bicubic) are parameter-free and require no weights. MOSR is an external, pretrained model released by its original authors and is not redistributed here (see the MOSR paper and its official release).
Usage
Download a checkpoint and run 4× super-resolution on a low-resolution .imzML file:
from huggingface_hub import hf_hub_download
weights = hf_hub_download("ZhihaoZhao/SwinMSI-weights", "swinmsi_best.pth")
# from the code repository
python evaluation/apply_superres_unet.py \
--input LR.imzML \
--output SR.imzML \
--model swinmsi_best.pth \
--device cuda
A one-click Colab demo that downloads a sample dataset and a checkpoint is provided in the
code repository at examples/quickstart_colab.ipynb.
Training
All models were trained from scratch on 70 public METASPACE MSI datasets (60 rodent-brain and 10 kidney sections), with low-resolution inputs synthesized by Gaussian point-spread-function blur followed by 4× bicubic downsampling. Training used PyTorch with BF16 mixed precision on a single NVIDIA RTX 4090. See the code repository for the full pipeline and configuration.
Citation
@article{zhao2026swinmsi,
title = {SwinMSI: Window-Attention Super-Resolution Exploiting Long-Range Self-Similarity for Mass Spectrometry Imaging},
author = {Zhao, Zhihao and Lv, Yuanxia and Zhuang, Yaoyu and Zhang, Zhimin and Wu, Qian and Lu, Hongmei},
year = {2026},
note = {Manuscript under review}
}
License
These weights are released under the Creative Commons Attribution 4.0 International (CC-BY-4.0) license, matching the accompanying dataset.
Sources
1 source
Sources
1 sourceVérifié 9 oct.
Download files
Artefacts du modèle
4 artefacts
Artefacts du modèle
4 artefactsExtraits de sources
2 extraits
Extraits de sources
2 extraits--- license: cc-by-4.0 tags: - mass-spectrometry-imaging - super-resolution - msi - swin-transformer - image-restoration library_name: pytorch --- # SwinMSI — Trained Model Weights Trained checkpoints for the paper **_"SwinMSI: Window-Attention Super-Resolution Exploiting Long-Range Self-Similarity for Mass Spectrometry Imaging."_** **SwinMSI** reconstructs a full high-resolution MSI dataset (all *m/z* channels) from a single fast, low-resolution acquisition, so that high spatial resolution can be traded for far shorter acquisition time (≈7–8× in our DESI experiments). Its Swin-Transformer (window-attention) backbone exploits the long-range self-similarity of MSI ion images to recover fine detail, operating on the MSI data alone (no co-registered optical modality). - 💻 **Code:** https://github.com/zhihaozhao98/SwinMSI - 📊 **Dataset (self-acquired DESI-MSI):** https://huggingface.co/datasets/ZhihaoZhao/MSI-SuperRes-DESI ## Files | File | Method | Params | Size | Notes | |------|--------|-------:|-----:|-------| | `swinmsi_best.pth` | **SwinMSI** (proposed) | 11.9 M | ~156 MB | SwinIR backbone, single Charbonnier loss, parameter-free pixel-space residual connection; 300 epochs @ 1e-4 then 100 epochs @ 1e-5 | | `unet.pth` | U-Net baseline | 31.2 M | ~357 MB | Convolutional encoder–decoder, identical training protocol | | `bbdm.pth` | BBDM (Brownian-bridge diffusion) | ~78 M | ~607 MB | 1000-step training, 250-step DDIM sampling at inference | | `ldm.pth` | LDM (latent diffusion) | ~81 M | ~617 MB | VAE + conditional latent diffusion U-Net | The interpolation baselines (bilinear, bicubic) are parameter-free and require no weights. **MOSR** is an external, pretrained model released by its original authors and is **not** redistributed here (see the [MOSR paper](https://doi.org/10.1038/s42256-023-00681-x) and its official release). ## Usage Download a checkpoint and run 4× super-resolution on a low-resolution `.imzML` file: ```python from huggingface_hub import hf_hub_download weights = hf_hub_download("ZhihaoZhao/SwinMSI-weights", "swinmsi_best.pth") ``` ```bash # from the code repository python evaluation/apply_superres_unet.py \ --input LR.imzML \ --output SR.imzML \ --model swinmsi_best.pth \ --device cuda ``` A one-click Colab demo that downloads a sample dataset and a checkpoint is provided in the code repository at `examples/quicks...
Source context: 0 downloads · 0 likes · Library pytorch · Repo ZhihaoZhao/SwinMSI-weights
