Improve model card for MedVSR: Add pipeline tag, paper, code, and usage details

README.md

@@ -1,3 +1,73 @@
----
-license: apache-2.0
----
+---
+license: apache-2.0
+pipeline_tag: image-to-image
+---
+
+# MedVSR: Medical Video Super-Resolution with Cross State-Space Propagation
+
+This model was presented in the paper [MedVSR: Medical Video Super-Resolution with Cross State-Space Propagation](https://huggingface.co/papers/2509.21265).
+The official code repository can be found at: [https://github.com/CUHK-AIM-Group/MedVSR](https://github.com/CUHK-AIM-Group/MedVSR).
+
+## Overview
+**MedVSR** is a tailored model for medical VSR.
+It first employs Cross State-Space Propagation (CSSP) to address the imprecise alignment by projecting distant frames as control matrices within state-space models, enabling the selective propagation of consistent and informative features to neighboring frames for effective alignment.
+It also features an Inner State-Space Reconstruction (ISSR) module that enhances tissue structures and reduces artifacts with joint long-range spatial feature learning and large-kernel short-range information aggregation.
+
+## Installation
+
+Clone this repository:
+```bash
+git clone https://github.com/CUHK-AIM-Group/MedVSR
+cd MedVSR
+
+conda create -n MedVSR python==3.9
+conda activate MedVSR
+
+pip install torch==2.1.1+cu121 torchvision==0.16.1+cu121 --extra-index-url https://download.pytorch.org/whl/cu121
+pip install -r requirements.txt
+
+pip install -e causal_conv1d>=1.1.0
+pip install -e mamba-1p1p1
+```
+
+## Dataset preparation
+
+For the preprocessed HyperKvasir, LDPolyp, and EndoVis18, please download from [huggingface link](https://huggingface.co/datasets/jeffrey423/MedVSR_dataset). Modify L14-16 and L39-40 to the extracted HyperKvasir training and validation folders.
+
+## Test the model
+
+Download our pretrained model at [here](https://huggingface.co/jeffrey423/MedVSR).
+
+```python
+python test_model.py -opt ./options/medvsr_train.yml --weight <PATH_TO_PRETRAINED_MEDVSR>
+```
+
+## Training
+```bash
+bash dist_train.sh 2 options/medvsr_train.yml 25623
+```
+
+## Citation
+```bibtex
+@inproceedings{liu2025medvsr,
+  title     = {MedVSR: Medical Video Super-Resolution with Cross State-Space Propagation},
+  author    = {Liu, Xinyu and Sun, Guolei and Wang, Cheng and Yuan, Yixuan and Konukoglu, Ender},
+  booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)},
+  year      = {2025}
+}
+```
+
+## Acknowledgement
+
+We sincerely thank the authors and contributors of the following projects for their awesome codebases, which have greatly benefited our work:
+
+- [BasicSR](https://github.com/XPixelGroup/BasicSR)
+- [IART](https://github.com/kai422/IART)
+- [RVRT](https://github.com/JingyunLiang/RVRT)
+- [Mamba](https://github.com/state-spaces/mamba)
+- [MambaVision](https://github.com/NVlabs/MambaVision)
+- [Vim](https://github.com/hustvl/Vim)
+
+## Contact
+
+Please contact [xinyuliu@link.cuhk.edu.hk](mailto:xinyuliu@link.cuhk.edu.hk) or open an issue.