NVIDIA Cosmos recipes turn depth video into RGB scenes for robot and AV training
NVIDIAAI · x · 2026-11-03
NVIDIA released new Cosmos simulation recipes that convert depth video into detailed RGB video, changing lighting, textures and backgrounds while preserving geometry and motion — e.g. turning a daytime drive into a rainy night with identical road layout and vehicle trajectories.
The recipes help developers generate training data and test policies for autonomous vehicles, robots, and even surgical applications.
The accompanying cosmos-framework is open-sourced on GitHub (595 stars), providing inference and training tooling, with checkpoints and recipes available for direct use.
Related event: NVIDIA Releases Cosmos Simulation Recipes and World Model Framework(4 posts)→
More from Embodied
- Industrial designer uses fal to iterate real hardware designs from photos, faster prototyping — OdinLovis · 2026-11-03
- NVIDIA Cosmos Simulation Recipes Turn Daytime Drives Into Rainy Nights With Trajectories Intact — NVIDIAAI · 2026-11-03
- AI Agent Performs Brain Drug Injection on a Live Mouse — ChuckDBrooks · 2026-11-03
- 3D World Simulator predicts appearance, geometry and touch at 50+ FPS on an RTX 5090 — YunzhuLiYZ · 2026-11-03
- Google's Suncatcher satellite runs Gemma 270mi n space—power limits mean only one TPU lit at a time — demian_ai · 2026-11-03
- Apple targets 2027 launch for $1,000 home robot, code-named J595 — Ars Technica AI · 2026-11-03