# SAW: Toward a Surgical Action World Model via Controllable and Scalable Video Generation arXiv: https://arxiv.org/abs/2603.13024 ยท HTML: https://mlsanity.com/paper/2603.13024/ ## Key facts - Cited by 9 papers in the map (data through 14 Oct 2026). - Placed in Medical and surgical world models, one of 11 directions in World models. - Builds on 21 of its 27 references that are in the map. - First posted on arXiv 13 Mar 2026. ## Placed in - World models / [Medical and surgical world models](https://mlsanity.com/wm/medical-and-surgical-world-models/) - Diffusion models / [Medical imaging and segmentation](https://mlsanity.com/diffusion/medical-imaging-and-segmentation/) ## Builds on (most cited first, 21 of 21) - [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020) - [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018) - [Flow Matching for Generative Modeling](https://mlsanity.com/paper/2210.02747/) (2022) - [Wan: Open and Advanced Large-Scale Video Generative Models](https://mlsanity.com/paper/2503.20314/) (2025) - [World Models](https://mlsanity.com/paper/1803.10122/) (2018) - [Depth Anything V2](https://mlsanity.com/paper/2406.09414/) (2024) - [Towards Accurate Generative Models of Video: A New Metric & Challenges](https://mlsanity.com/paper/1812.01717/) (2018) - [A Closer Look at Spatiotemporal Convolutions for Action Recognition](https://mlsanity.com/paper/1711.11248/) (2017) - [SAM 3: Segment Anything with Concepts](https://mlsanity.com/paper/2511.16719/) (2025) - [LTX-Video: Realtime Video Latent Diffusion](https://mlsanity.com/paper/2501.00103/) (2024) - [Learning Interactive Real-World Simulators](https://mlsanity.com/paper/2310.06114/) (2023) - [EndoNet: A Deep Architecture for Recognition Tasks on Laparoscopic Videos](https://mlsanity.com/paper/1602.03012/) (2016) - [Comparative Validation of Machine Learning Algorithms for Surgical Workflow and Skill Analysis with the HeiChole Benchmark](https://mlsanity.com/paper/2109.14956/) (2021) - [On the Content Bias in Fr'echet Video Distance](https://mlsanity.com/paper/2404.12391/) (2024) - [Rendezvous in Time: An Attention-based Temporal Fusion approach for Surgical Triplet Recognition](https://mlsanity.com/paper/2211.16963/) (2022) - [Sim-To-Real Transfer for Visual Reinforcement Learning of Deformable Object Manipulation for Robot-Assisted Surgery](https://mlsanity.com/paper/2406.06092/) (2024) - [SurgSora: Object-Aware Diffusion Model for Controllable Surgical Video Generation](https://mlsanity.com/paper/2412.14018/) (2024) - [Surgical Visual Understanding (SurgVU) Dataset](https://mlsanity.com/paper/2501.09209/) (2025) - [HieraSurg: Hierarchy-Aware Diffusion Model for Surgical Video Generation](https://mlsanity.com/paper/2506.21287/) (2025) - [Deformable Models for Surgical Simulation: A Survey](https://mlsanity.com/paper/1909.03363/) (2019) - [Expanded Comprehensive Robotic Cholecystectomy Dataset (CRCD)](https://mlsanity.com/paper/2412.12238/) (2024) ## Built on by (most cited first, 9 of 9) - [From Articulated Kinematics to Routed Visual Control for Action-Conditioned Surgical Video Generation](https://mlsanity.com/paper/2605.08712/) (2026) - [Medical world models in healthcare: foundations, applications, and challenges for trustworthy clinical translation](https://mlsanity.com/paper/2607.25242/) (2026) - [SurgVista: Long-Horizon Surgical World Modeling with Plausible Instrument-Tissue Dynamics](https://mlsanity.com/paper/2606.19889/) (2026) - [SurgWMBench: A Vision-Based Benchmark for World-Modeling Surgical Instrument Motion Planning](https://mlsanity.com/paper/2608.08070/) (2026) - [CrossScope: A Role-Asymmetric World Model for Joint Dual-Scope Surgical Video Prediction](https://mlsanity.com/paper/2608.03211/) (2026) - [Surg-UniWorld: A Unified Surgical World Model with Multimodal Control Experts](https://mlsanity.com/paper/2608.06770/) (2026) - [Towards Surgical World-Action Modeling: A Preliminary Joint Visual-Trajectory Forecasting for Surgical Motion Planning](https://mlsanity.com/paper/2608.20284/) (2026) - [SurgCast: Action-Conditioned Future Skeletons for Controllable Surgical World Models](https://mlsanity.com/paper/2610.15645/) (2026) - [SonoWorld: Towards Interactive Pose-Controllable Ultrasound World Models](https://mlsanity.com/paper/2610.19327/) (2026) ## Abstract (arXiv) A surgical world model capable of generating realistic surgical action videos with precise control over tool-tissue interactions can address fundamental challenges in surgical AI and simulation -- from data scarcity and rare event synthesis to bridging the sim-to-real gap for surgical automation. However, current video generation methods, the very core of such surgical world models, require expensive annotations or complex structured intermediates as conditioning signals at inference, limiting their scalability. Other approaches exhibit limited temporal consistency across complex laparoscopic scenes and do not possess sufficient realism. We propose Surgical Action World (SAW) -- a step toward surgical action world modeling through video diffusion conditioned on four lightweight signals: language prompts encoding tool-action context, a reference surgical scene, tissue affordance mask, and 2D tool-tip trajectories. We design a conditional video diffusion approach that reformulates video-to-video diffusion into trajectory-conditioned surgical action synthesis. The backbone diffusion model is fine-tuned on a custom-curated dataset of 12,044 laparoscopic clips with lightweight spatiotemporal conditioning signals, leveraging a depth consistency loss to enforce geometric plausibility without requiring depth at inference. SAW achieves state-of-the-art temporal consistency (CD-FVD: 199.19 vs. 546.82) and strong visual quality on held-out test data. Furthermore, we demonstrate its downstream utility for (a) surgical AI, where augmenting rare actions with SAW-generated videos improves action recognition (clipping F1-score: 20.93% to 43.14%; cutting: 0.00% to 8.33%) on real test data, and (b) surgical simulation, where rendering tool-tissue interaction videos from simulator-derived trajectory points toward a visually faithful simulation engine.