Point Tracking in Surgery--The 2025 Surgical Tattoos in Infrared Challenge (STIRC2025)

2026-07-14

AI Summary

This work addresses the longstanding absence of a unified benchmark for keypoint tracking in surgical settings, a critical capability for downstream tasks such as segmentation and 3D reconstruction. To bridge this gap, the authors initiated and organized the STIRC2025 Challenge, establishing the first public evaluation platform dedicated to infrared point tracking in surgical scenarios. Built upon the newly released Surgical Tattoo Infrared (STIR) dataset, the benchmark systematically evaluates algorithmic performance across both in vivo and ex vivo sequences, emphasizing tracking accuracy and inference efficiency. The challenge attracted seven participating teams and provided standardized data, evaluation metrics, and a low-latency testing framework. This effort successfully established a reproducible benchmark, significantly advancing the development of surgical visual perception algorithms.

Abstract

Point tracking in surgery is crucial to enable applications in downstream tasks such as segmentation, 3D reconstruction, virtual tissue landmarking, autonomous probe-based scanning, and subtask autonomy. This paper introduces the 2025 iteration of a point tracking challenge to address this, wherein participants submit their algorithms for quantification. Their algorithms are evaluated using a dataset named surgical tattoos in infrared (STIR), with the challenge named the STIR Challenge 2025 (STIRC2025). The STIR Challenge 2025 comprises two quantitative components: accuracy and efficiency. The accuracy component tests the accuracy of algorithms on in vivo and ex vivo sequences. The efficiency component tests algorithm inference latency. The challenge was conducted as a part of MICCAI EndoVis 2025, and seven teams participated in this challenge. In this paper we summarize the challenge results and participant methods. The challenge dataset is available at: https://zenodo.org/records/20191078, and the code for baseline models and metrics calculation is available here: https://github.com/athaddius/STIRMetrics

Problem

• point tracking
• surgical tattoos
• infrared imaging
• surgical video analysis
• medical image computing

Innovation

• point tracking
• surgical tattoos
• infrared imaging
• benchmark challenge
• algorithm efficiency