# D4RT: Teaching AI to see the world in four dimensions

DevFeed: [D4RT: Teaching AI to see the world in four dimensions](<https://devfeed.tech/articles/d4rt-teaching-ai-to-see-the-world-in-four-dimensions-6144.md>)

Original publisher: [Read original article](<https://deepmind.google/blog/d4rt-teaching-ai-to-see-the-world-in-four-dimensions/>)

Author: Guillaume Le Moing; Mehdi S. M. Sajjadi

Published: 2026-01-16T10:39:00Z

Content type: article

Language: en

Sources: [Google DeepMind News](<https://devfeed.tech/sources/google-deepmind-news.md>)

Topics: [AI, ML & Data Engineering](<https://devfeed.tech/topics/ai-ml-data-engineering.md>)

Tags: [3d](<https://devfeed.tech/tags/3d.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-models](<https://devfeed.tech/tags/ai-models.md>), [architecture](<https://devfeed.tech/tags/architecture.md>), [framework](<https://devfeed.tech/tags/framework.md>), [real-time](<https://devfeed.tech/tags/real-time.md>), [research](<https://devfeed.tech/tags/research.md>), [robotics](<https://devfeed.tech/tags/robotics.md>), [transformer-architecture](<https://devfeed.tech/tags/transformer-architecture.md>), [video](<https://devfeed.tech/tags/video.md>)

## AI overview

D4RT is a unified AI model for reconstructing and tracking dynamic 3D scenes over time from video. It uses an encoder-decoder Transformer and a query-based mechanism, with claimed efficiency gains for real-time robotics and augmented-reality uses.

## Source excerpt

D4RT: Unified, efficient 4D reconstruction and tracking up to 300x faster than prior methods.