SciVid STIR: Surgical Tattoos in Infrared Point-Tracking Clips of Soft Tissue in Endoscopic Video (Google DeepMind)

Provider
Google DeepMind (SciVid); source data University of British Columbia and Intuitive Surgical
License
CC-BY-4.0 (source)
Stored at
Google Cloud Storage, gs://scivid/full/stir (us)
Access
Free and public. No account with the data provider is needed.
Category
Health & Biomedical
Source
https://arxiv.org/abs/2309.16782

About this dataset

Preprocessed STIR (Surgical Tattoos in Infrared) clips for point tracking on deforming soft tissue in surgical endoscopy video, as packaged in the SciVid benchmark. STIR, from the University of British Columbia and Intuitive Surgical, marks tissue with infrared-visible tattoo points that are invisible in the visible-light video, giving ground-truth start and end positions of tracked points across surgical sequences. SciVid filtered and downsampled the clips and normalized query and target points by image size. The folder holds three sets of 100 shards: full_val_stir, short_val_stir and test_stir. There is no training split; models are evaluated on how well tracking transfers to tissue motion in minimally invasive surgery. SciVid (Hasson et al., SciVid: Cross-Domain Evaluation of Video Models in Scientific Applications, ICCV 2025, arXiv:2507.03578) is a five-task benchmark for video foundation models in science; this folder is one task. Files are ArrayRecord shards, read with the array_record Python package or the loaders in the google-deepmind/scivid repository. License: SciVid materials CC BY 4.0 (Google DeepMind); STIR is under a Creative Commons Attribution license at IEEE DataPort (DOI 10.21227/w8g4-g548). Cite SciVid and the STIR paper, arXiv:2309.16782.

How to access this dataset in Python

import gcsfs
fs = gcsfs.GCSFileSystem(token='anon')
fs.ls('scivid/full/stir/', detail=False)[:10]

Lists the files with anonymous access. Runs on any machine, with no cloud account.

Data structure

Files

Example file: full/stir/

Analyze this dataset without downloading it

On Scigantic, SciVid STIR: Surgical Tattoos in Infrared Point-Tracking Clips of Soft Tissue in Endoscopic Video (Google DeepMind) opens in a hosted JupyterLab notebook with the data already mounted, so you can read files where they are stored instead of copying them first. Each notebook includes an AI assistant that can see the mounted files and write and run analysis code. Open the dataset page to launch a notebook, or browse the full catalog.

This page is also available as Markdown and as JSON.

Related Health & Biomedical datasets