STIR Challenge 2025 Dataset

This is the STIR Challenge 2025 (STIRC2025) dataset for evaluating point tracking and reconstruction methods in surgery. This a new, previously unreleased, dataset that was used in the STIR Challenge 2025 at MICCAI's EndoVis. For details, refer to the STIRC2025 Challenge Paper.

This data has the same format as the larger STIR training and validation dataset (STIROrig). Dataset info for the prior year's challenge can be found in the STIRC2024 Challenge Paper, and data can be downloaded from https://zenodo.org/records/14803158
The STIR training and validation dataset (STIROrig) details are available in the dataset curation and creation paper (equivalent paper on arxiv). STIROrig download link: https://dx.doi.org/10.21227/w8g4-g548

Data Description

This dataset includes multiple collections (folders).  Each collection includes multiple clips with stereo videos.
Under each of 'left' and 'right' folders are:
seq** folders (seq00-seq14, for example). Each 'seq' folder corresponds to an action.
For example, left/seq01 corresponds to the same recording as right/seq01 for the right camera. All images and videos are stereo rectified, and camera calibration is also provided in `calib.json`.

Each 'seq**' folder contains:
- frames (a folder containing visible light video as a mp4)
- segmentation (contains start and end binary segmentation pngs)
- icgstartseg.png (start segmentation)
- icgendseg.png (finish segmentation)
- <STARTTIME>ms_icgstart.png (starting IR image)
- <STARTTIME>ms_icgend.png (finishing IR image)

Quantification

Use the STIRMetrics repo to assist with quantification, we use the TAP-Vid metric of average accuracy, δx, over thresholds. The 2D metric is averaged over accuracy thresholds of [4, 8, 16, 32, 64] pixels. The 3D metric is averaged over accuracy thresholds of [2, 4, 8, 16, 32] millimetres.

Refer to the STIRC2025 challenge paper for additional analysis.

Terms

By using this dataset, you agree to cite the 2025 challenge paper:

@misc{schmidt2026pointtrackingsurgerythe2025,
      title={Point Tracking in Surgery--The 2025 Surgical Tattoos in Infrared Challenge (STIRC2025)}, 
      author={Adam Schmidt and Mert Asim Karaoglu and Zijian Wu and Jiaming Zhang and Yuxin Chen and Tim Salcudean and Ho-Gun Ha and Minkang Jang and Kyungmin Jung and Ihsan Ullah and Hyunki Lee and Suresh Guttikonda and Sarah Latus and Alexander Schlaefer and Xinkai Zhao and Yuichiro Hayashi and Masahiro Oda and Takayuki Kitasaka and Kensaku Mori and Peng Liu and Chenyang Li and Stefanie Speidel and Aoife Gardiner and Agostino Stilli and Danail Stoyanov and Francisco Vasconcelos and Anwesa Choudhuri and Meng Zheng and Zhongpai Gao and Benjamin Planche and Van Nguyen Nguyen and Terrence Chen and Ziyan Wu and Alexander Ladikos and Omid Mohareri},
      year={2026},
      eprint={2607.12939},
      archivePrefix={arXiv},
      primaryClass={cs.CV},
      url={https://arxiv.org/abs/2607.12939}, 
}

And the initial dataset paper:

@article{schmidt2024surgical,
  title={Surgical Tattoos in Infrared: A Dataset for Quantifying Tissue Tracking and Mapping},
  author={Schmidt, Adam and Mohareri, Omid and DiMaio, Simon and Salcudean, Septimiu E},
  journal={IEEE Transactions on Medical Imaging},
  year={2024},
  publisher={IEEE}
}