CVMar 31

Scaling Video Pretraining for Surgical Foundation Models

arXiv:2603.2996659.4
AI Analysis

This work addresses the need for reproducible and scalable foundation models in surgical video understanding, which is incremental by building on existing self-supervised learning techniques with a large curated dataset.

The authors tackled the problem of limited data scale and inconsistent evaluation in surgical video understanding by proposing SurgRec, a scalable pretraining recipe, which achieved superior performance across 16 downstream datasets compared to existing methods.

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 spanning endoscopy, laparoscopy, cataract, and robotic surgery. Building on this corpus, we develop a unified pretraining pipeline with balanced sampling and standardize a reproducible benchmark across 16 downstream datasets and four clinical domains with consistent data splits. Across extensive comparisons against SSL baselines and vision-language models, SurgRec consistently achieves superior performance across downstream datasets. In contrast, VLMs prove unreliable for fine-grained temporal recognition, exhibiting both performance gaps and sensitivity to prompt phrasing. Our work provides a reproducible, scalable foundation for the community to build more general surgical video models. All code, models, and data will be publicly released.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes