NVIDIA's Foundation4D brings video priors to lidarless NuRec, releases depth labels for 1,253 driving clips
lealtaixe · x · 2026-10-29
NVIDIA researcher lealtaixe unveiled Foundation4D, extending video understanding to simulation: the model provides priors for lidarless NuRec and recovers metric depth, multi-camera extrinsics, and ego-motion from multi-camera video. Factorized attention combines views and time efficiently, while global pose optimization turns local predictions into coherent camera trajectories.
The team also released dense depth and occupancy labels for 1,253 driving clips so others can measure progress across tasks.
More from Embodied
- Raven Prism launches: a full Linux computer on your face, first batch ships in January — Scobleizer · 2026-10-29
- RealSense's new Min-Z update lets robots see objects just 2cm from their fingertips — chrismatthieu · 2026-10-29
- Humanoid robots don't need to scan the whole ground: structured perception could slash terrain training — breadli428 · 2026-10-29
- New Meshtastic tutorial shows how to set up a solar-powered LoRa repeater — ShawnHymel · 2026-10-29
- GPT-6 Sol beats Gemini 3.8 Flash 1012–972 on Physical Agent Capability Index — qinzytech · 2026-10-29
- Mila's open-source Harpia uses drones + AI to survey hundreds of tree crowns in a day — Mila_Quebec · 2026-10-29