Skip to content

RobotsNAV·01Robots VideosNAV·02Videos ComponentsNAV·03Components PapersNAV·04Papers BlogNAV·05Blog Tech CrowdfundingNAV·06Tech Crowdfunding Open SourceNAV·07Open Source World ModelsNAV·08World Models LeaderboardNAV·09Leaderboard Industry ChainNAV·10Industry Chain InvestNAV·11Invest Creative WorkshopNAV·12Creative Workshop

physical-ai

[●●●]FETCHING

RobotWorld

Robotics knowledge and video hub · © 2026

@McQueenFuFollow Tags About DMCA946 demos330 papers873 components

← Back to Videos

Nine phone photos become a walkable 3D office

Loading video

Loading video

Scenario shows GPT-6 Astra plus Scenario MCP turning nine phone photos of its office into a walkable 3D room: Astra infers the layout and rebuilds geometry in Blender, while the MCP pulls real carpet, wood and metal materials straight from the photos.

3D reconstruction Scene Understanding Digital twins Blender MCP

Category: perception

Author: @Scenario_gg

Date: 2026-09-16T00:00:00

Duration: 26.633s

Source: https://x.com/Scenario_gg/status/2100161753564713405

Related Videos

Prevu3D x NavVis VLX4: Reality Capture Straight Into Revit

Prevu3D x NavVis VLX4: Reality Capture Straight Into Revit

@tokufxug · 23 views · 2026-09-18

Reality CaptureScan-to-CADRevit

Carveout Brings Object-Level Understanding to 3D Gaussian Splat Scenes

Carveout Brings Object-Level Understanding to 3D Gaussian Splat Scenes

@smallfly · 111 views · 2026-09-10

3D Gaussian SplattingInstance SegmentationSAM 3

microSLAM: Monocular SLAM for Interactive 3D Environments

microSLAM: Monocular SLAM for Interactive 3D Environments

@ZenoInMotion · 142 views · 2026-09-10

SLAMMonocular Vision3D reconstruction

VidMap at ECCV 2026: Video-Based Structure-from-Motion

VidMap at ECCV 2026: Video-Based Structure-from-Motion

@pesarlin · 195 views · 2026-09-07

Structure-from-Motion3D reconstructionCamera Pose Estimation

MINT open-source egocentric hand motion reconstruction

MINT open-source egocentric hand motion reconstruction

@wuji_global · 141 views · 2026-09-10

Motion CaptureEgocentric VisionHand Pose Estimation

VidMap: Exploiting temporal structure for video-based Structure-from-Motion

VidMap: Exploiting temporal structure for video-based Structure-from-Motion

@zador_pataki · 141 views · 2026-08-07

SLAMSfMECCV2026