NVIDIA Open-Sources Surgical World Model Cosmos3-H-Dreams, Enabling Real-Time Surgical Scene Generation on a Single GPU
NVIDIA has released and open-sourced the real-time generative surgical world model Cosmos3-H-Dreams, which can generate surgical scenes in real time based on robot operation instructions, simulating instrument movement, tissue retraction, and deformation. The model is built on the 16-billion-parameter Cosmos3-H-Embodied-Nano, with training data comprising approximately 526 minutes of real surgical video selected from 4,792 surgical recordings, and it supports 28-dimensional action input. Using teacher-student distillation and the FlashDreams streaming inference framework, the model requires only a single NVIDIA RTX PRO 6000 GPU for real-time interaction, and two student model versions with 4-step and 2-step denoising have been open-sourced.
Why read this
AI score 70
The original text details the model's parameter scale, training data sources, and single-GPU real-time inference approach, offering insight into how surgical world models move from desktop tasks to clinical scenarios.
Topics
Body
The English body is being prepared. You can open the original source.