← Back to Videos

Fire3D Turns RGB Video into Simulation-Ready 3D Scenes

Loading video

Fire3D converts an unsegmented image or casual RGB video into a complete textured, simulation-ready 3D scene in under a minute. It discovers objects and estimates their 6-DoF poses without supplied masks, boxes or prompts.

3D reconstruction Simulation Embodied AI 6-DoF Pose Fire3D University of Illinois Cornell University Simulation Environment

Category: research

Author: @hongchix

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

Duration: 31.4s

Source: https://x.com/hongchix/status/2097699251690131836

Reference: https://xiahongchi.github.io/Fire3D/

SimWorld Studio: Evolving Environments for Embodied Agents

SimWorld Studio: Evolving Environments for Embodied Agents

@simworld_ai · 732 views · 2026-09-10

SimulationEmbodied AI

Odyssey-3: World Models as Training Grounds for Agents

Odyssey-3: World Models as Training Grounds for Agents

@olivercameron · 1.1k views · 2026-09-15

World ModelsEmbodied AI

HiP3R Reconstructs 10,000-Frame Videos in 3D

HiP3R Reconstructs 10,000-Frame Videos in 3D

@zunnanxu · 47 views · 2026-10-26

3D reconstructionLong Video

AGIBOT WORLD 2026 Release 4: Physical Reasoning Dataset for Real-World Decisions

AGIBOT WORLD 2026 Release 4: Physical Reasoning Dataset for Real-World Decisions

@AGIBOTofficial · 103 views · 2026-10-23

Embodied AIPhysical Reasoning

Same VLA, three data sources: Human Archive OTS wins on task success

Same VLA, three data sources: Human Archive OTS wins on task success

@babugi28 · 151 views · 2026-10-15

VLAPre-training Data

RT-SAFE: real-time embodied-agent safety benchmarking

RT-SAFE: real-time embodied-agent safety benchmarking

@XTRose88 · 628 views · 2026-10-06

Embodied AISafety Evaluation

As an Amazon Associate, we earn from qualifying purchases.