Skip to content
RobotWorld
← Back to Videos

DeepMind D4RT turns a video into a 4D world

Loading video
Loading video

Google DeepMind, UCL, and Oxford introduce D4RT, which jointly understands depth, motion, 3D correspondences, and camera parameters from a single video for 4D world models and embodied perception.

D4RT4D WorldWorld ModelsSpatial AI3D reconstructionvision perceptionVideo understandingGoogle DeepMindEmbodied AIAlacritic_SuperVisual perception
Category: perception
Author: @Alacritic_Super
Date: 2026-08-31T00:00:00
Duration: 213.379s
Source: https://x.com/Alacritic_Super/status/2094468568431874236
Reference: https://arxiv.org/abs/2512.08924

Related Videos

ABot-Recon turns driving video into 3D scenes
0:16

ABot-Recon turns driving video into 3D scenes

@HuggingApps · 693 views · 2026-08-31
ABot-Recon3D reconstructionSpatial AI
Google Gemini agentic video understanding
0:24

Google Gemini agentic video understanding

@Gorden_Sun · 633 views · 2026-09-02
GoogleGeminiAgentic video understanding
ABot-Recon Streaming 3D Reconstruction
0:15

ABot-Recon Streaming 3D Reconstruction

@IndieDevHailey · 614 views · 2026-08-29
SLAMAMapABot-Recon
LiteReality-Agent turns room scans into interactive 3D scenes
0:58

LiteReality-Agent turns room scans into interactive 3D scenes

@ZheningHuang · 457 views · 2026-08-07
LiteRealityRGB-DScene Reconstruction
pixelml-av + Grok + Jev: Agentic Video Understanding 100x Cheaper and 10x Faster Than Gemini 3.8 Flash
1:05

pixelml-av + Grok + Jev: Agentic Video Understanding 100x Cheaper and 10x Faster Than Gemini 3.8 Flash

@seanphan · 571 views · 2026-09-19
Video understandingAgentic Video QARetrieval-Augmented Generation
Grounded API: Robot Perception and SLAM
1:14

Grounded API: Robot Perception and SLAM

@GroundedSI · 767 views · 2026-09-16
Robot perceptionSLAMHand Tracking

As an Amazon Associate, we earn from qualifying purchases.