SceneAgent: An Agentic Pipeline from 3D and 4D Captures to Simulation Envelopes
Overview
SceneAgent is a research paper introducing an agentic pipeline that converts 3, 4D captures into simulation environments through object reconstruction, physical modeling, and error correction. It processes various capture types and supports policy learning with diverse object variants and scripted demonstrations. The method outperforms existing approaches in F1 scores and dynamic IoU, enabling simulated interactions and preliminary real-world policy transfer.
From arXiv Robotics — research abstracts
Event evidence and corrections
0 attributed source owners. Ownership does not establish independent confirmation. Quantities are reported separately and are never added together.
Reported quantity · cm: 1 other · Basis not reported
“(3DGS), photogrammetry, LiDAR captures, AI-generated 3DGS scenes, and 4D videos of dynamic scenes, and combines object segmentation, physical parameter estimation, part decomposition, articulation, and deformable simulation. To support policy learning, SceneAgent generates diverse object variants ("digital sisters") and scripted demonstrations. On a cluttered bin scene from GraspClutter6D, SceneAgent raises F1 at 1”
Exact source · revision 1Source owner not reported
Evidence dependency changes (2)
- 2026-10-30T19:47:53.047Z · evidence updated · source revision 1. Evidence extraction was updated; current source attributions are shown above.
- 2026-10-30T19:47:46.189Z · evidence updated · source revision 1. Evidence extraction was updated; current source attributions are shown above.
Report timeline
Follow attributed reports and material updates.
- arXiv Robotics — research abstractsSignalSceneAgent: An Agentic Pipeline from 3D and 4D Captures to Simulation Environments
SceneAgent is a research paper introducing an agentic pipeline that converts 3, 4D captures into simulation environments through object reconstruction, physical modeling, and error correction. It processes various capture types and supports policy learning with diverse object variants and scripted demonstrations. The method outperforms existing approaches in F1 scores and dynamic IoU, enabling simulated interactions and preliminary real-world policy transfer.
Timezone · UTC
Article dates follow your selected timezone. Briefing editions use Hong Kong time (UTC+8).