Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Wu, Jinlin, Holm, Felix, Chen, Chuxi, Wang, An, Hu, Yaxin, Ye, Xiaofan, Zang, Zelin, Xu, Miao, Zhou, Lihua, Liao, Huai, Chan, Danny T. M., Feng, Ming, Poon, Wai S., Ren, Hongliang, Yi, Dong, Navab, Nassir, Meng, Gaofeng, Luo, Jiebo, Liu, Hongbin, Lei, Zhen
Format: Preprint
Veröffentlicht: 2026
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2602.05638
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866908972628312064
author Wu, Jinlin
Holm, Felix
Chen, Chuxi
Wang, An
Hu, Yaxin
Ye, Xiaofan
Zang, Zelin
Xu, Miao
Zhou, Lihua
Liao, Huai
Chan, Danny T. M.
Feng, Ming
Poon, Wai S.
Ren, Hongliang
Yi, Dong
Navab, Nassir
Meng, Gaofeng
Luo, Jiebo
Liu, Hongbin
Lei, Zhen
author_facet Wu, Jinlin
Holm, Felix
Chen, Chuxi
Wang, An
Hu, Yaxin
Ye, Xiaofan
Zang, Zelin
Xu, Miao
Zhou, Lihua
Liao, Huai
Chan, Danny T. M.
Feng, Ming
Poon, Wai S.
Ren, Hongliang
Yi, Dong
Navab, Nassir
Meng, Gaofeng
Luo, Jiebo
Liu, Hongbin
Lei, Zhen
contents While foundation models have advanced surgical video analysis, current approaches rely predominantly on pixel-level reconstruction objectives that waste model capacity on low-level visual details, such as smoke, specular reflections, and fluid motion, rather than semantic structures essential for surgical understanding. We present SurgMotion, a video-native foundation model that shifts the learning paradigm from pixel-level reconstruction to latent motion prediction. Built on the Video Joint Embedding Predictive Architecture (V-JEPA), SurgMotion introduces three key technical innovations tailored to surgical videos: (1) motion-guided latent masked prediction to prioritize semantically meaningful regions, (2) spatiotemporal affinity self-distillation to enforce relational consistency, and (3) spatiotemporal feature diversity regularization (SFDR) to prevent representation collapse in texture-sparse surgical scenes. To enable large-scale pretraining, we curate SurgMotion-15M, the largest surgical video dataset to date, comprising 3,658 hours of video from 50 sources across 13 anatomical regions. Extensive experiments across 17 benchmarks demonstrate that SurgMotion significantly outperforms state-of-the-art methods on surgical workflow recognition, achieving 14.6 percent improvement in F1 score on EgoSurgery and 10.3 percent on PitVis; on action triplet recognition with 39.54 percent mAP-IVT on CholecT50; as well as on skill assessment, polyp segmentation, and depth estimation. These results establish SurgMotion as a new standard for universal, motion-oriented surgical video understanding.
format Preprint
id arxiv_https___arxiv_org_abs_2602_05638
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle SurgMotion: A Video-Native Foundation Model for Universal Understanding of Surgical Videos
Wu, Jinlin
Holm, Felix
Chen, Chuxi
Wang, An
Hu, Yaxin
Ye, Xiaofan
Zang, Zelin
Xu, Miao
Zhou, Lihua
Liao, Huai
Chan, Danny T. M.
Feng, Ming
Poon, Wai S.
Ren, Hongliang
Yi, Dong
Navab, Nassir
Meng, Gaofeng
Luo, Jiebo
Liu, Hongbin
Lei, Zhen
Computer Vision and Pattern Recognition
While foundation models have advanced surgical video analysis, current approaches rely predominantly on pixel-level reconstruction objectives that waste model capacity on low-level visual details, such as smoke, specular reflections, and fluid motion, rather than semantic structures essential for surgical understanding. We present SurgMotion, a video-native foundation model that shifts the learning paradigm from pixel-level reconstruction to latent motion prediction. Built on the Video Joint Embedding Predictive Architecture (V-JEPA), SurgMotion introduces three key technical innovations tailored to surgical videos: (1) motion-guided latent masked prediction to prioritize semantically meaningful regions, (2) spatiotemporal affinity self-distillation to enforce relational consistency, and (3) spatiotemporal feature diversity regularization (SFDR) to prevent representation collapse in texture-sparse surgical scenes. To enable large-scale pretraining, we curate SurgMotion-15M, the largest surgical video dataset to date, comprising 3,658 hours of video from 50 sources across 13 anatomical regions. Extensive experiments across 17 benchmarks demonstrate that SurgMotion significantly outperforms state-of-the-art methods on surgical workflow recognition, achieving 14.6 percent improvement in F1 score on EgoSurgery and 10.3 percent on PitVis; on action triplet recognition with 39.54 percent mAP-IVT on CholecT50; as well as on skill assessment, polyp segmentation, and depth estimation. These results establish SurgMotion as a new standard for universal, motion-oriented surgical video understanding.
title SurgMotion: A Video-Native Foundation Model for Universal Understanding of Surgical Videos
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2602.05638