SOURCE-LINKED INTELLIGENCE

Demonstration Synthesis from a Single Scan via Gaussian Splatting for Visuomotor Policy Learning

arXiv · AI, language, vision and robotics · article · Sep 17, 2026 · UTC

Training a visuomotor policy calls for abundant demonstrations that closely match the target environment, yet collecting them anew remains expensive. Existing demonstration synthesis methods reduce this cost but remain constrained by high manual effort, limited visual fidelity, or heavy reliance on physics simulators. This paper introduces GaussianFactory, a high-fidelity data engine that mass-produces demonstrations with a single video scan as its only human input and no physics engine in the generation loop. Specifically, GaussianFactory reconstructs the scene as an editable 3D Gaussian Spla

Read original source ↗ Open in workspace

recordType

paper

region

Global