We're helping AI to see the 3D world in motion as humans do. 🌐 Enter D4RT: a un...

Google DeepMind (@GoogleDeepMind)

2026-01-22 | ❤️ 3187 | 🔁 440 | 💬 93

---

We’re helping AI to see the 3D world in motion as humans do. 🌐

Enter D4RT: a unified model that turns video into 4D representations faster than previous methods - enabling it to understand space and time. This is how it works 🧵

미디어

---

🔗 Related

• what-if-sim-and-reality-were-one-this-system-keeps-them-in — 주제: AI-ML, Vision/3D
• introducing-shaper-a-method-for-robust-conditional-3d-shape — 주제: AI-ML, Vision/3D
• if-youve-ever-tried-to-create-3dgs-scenes-from-photos-taken — 주제: AI-ML, Vision/3D
• iggt-instance-grounded-geometry-transformer-for-semantic-3d — 주제: AI-ML, Vision/3D
• luxremix-lighting-decomposition-and-remixing-for-indoor — 주제: AI-ML, Vision/3D

Tags

Vision-3D AI-ML