← Back to Benchmarks
simmediumvision-robotmetric · varies

Scaling Video Pretraining for Surgical Foundation Models

Description

Surgical video understanding is essential for computer-assisted interventions, yet existing surgical foundation models remain constrained by limited data scale, procedural diversity, and inconsistent evaluation, often lacking a reproducible training pipeline. We propose SurgRec, a scalable and reproducible pretraining recipe for surgical video understanding, instantiated with two variants: SurgRec-MAE and SurgRec-JEPA. We curate a large multi-source corpus of 10,535 videos and 214.5M frames span

Source

http://arxiv.org/abs/2603.29966v2