Metraipolis › archive › dc_65b17837e033
Beyond Masks and Trajectories: Flow-Guided Latent Action Injection for Stable Surgical Video Generation — arXiv:2610.09800
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.09800
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-08T12:47:37.970Z
- SHA-256 of the archived text
22b274002635e63192dc44202168a9e33d186bf98003faec40f18671cf8efe17- Stable URL of this page
https://metraipolis.com/documento/dc_65b17837e033
How to cite
Beyond Masks and Trajectories: Flow-Guided Latent Action Injection for Stable Surgical Video Generation — arXiv:2610.09800 — arXiv (en), https://arxiv.org/abs/2610.09800 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_65b17837e033 (Metraipolis archive dc_65b17837e033, sha256 22b274002635e63192dc44202168a9e33d186bf98003faec40f18671cf8efe17)
BibTeX
@misc{dc65b17837e033,
title = {Beyond Masks and Trajectories: Flow-Guided Latent Action Injection for Stable Surgical Video Generation — arXiv:2610.09800},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.09800},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_65b17837e033; sha256 22b274002635e63192dc44202168a9e33d186bf98003faec40f18671cf8efe17},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.09800. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Surgical video generation holds substantial potential for surgical education, simulation, and data augmentation, yet generating surgical videos with realistic and clinically plausible motion remains challenging. Most existing methods rely on auxiliary conditions, such as masks, trajectories, depth, or reference videos, to achieve visually plausible synthesis. Yet, these auxiliary conditions typically require additional manual annotation or specialized acquisition, making it difficult to scale such methods beyond small, curated datasets. This motivates the need for a reference-free architecture capable of generating high-quality surgical video without requiring auxiliary visual conditions at inference time. We propose FLAIR, a Flow-guided LatentAction Injection framework for Reference-free surgical video generation. FLAIR learns action priors from optical flow of real surgical videos, dynamically predicts corresponding latent action representation from an input prompt, and injects it into a frozen base model to generate surgical videos with improved action consistency. We further construct SurgActionClip-30K, the first large-scale surgical vision dataset comprising action-centric segmented clips and structured caption labels, addressing the persistent lack of fine-grained, action-centric surgical datasets. Lastly, we introduce SurgMetrics, the first surgical domain-specific evaluation metrics for quantifying the quality of generated surgical videos, addressing the persistent absence of clinically grounded evaluation standards in this domain. Extensive experiments demonstrate that FLAIR enables generating high-quality surgical videos using text-only inference without auxiliary conditions, and validation in SurgMetrics demonstrates its strength in alignment with human perception compared to traditional metrics. Tema degli esploratori: statistica e scienza dei dati (elenco arXiv cs.CV, nuovi lavori del giorno). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2610.09800 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-08T12:18:15.417Z dalla pagina https://arxiv.org/list/cs.CV/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).