SOURCE-LINKED INTELLIGENCE

WorldSculpt: Generating Compositional Worlds from Grounded Videos

arXiv · AI, language, vision and robotics · article · Sep 4, 2026 · UTC

We study the problem of generating a compositional 3D representation of a cluttered scene containing hundreds of objects. The goal is to represent the scene as a collection of individual object meshes placed in a shared world frame, as required by downstream applications such as gaming, AR/VR, simulation, and robotics. This task is challenging in densely cluttered scenes, where objects heavily occlude one another and each view reveals only a fraction of their geometry. Geometry-based approaches typically reconstruct the scene as a single representation and leave incomplete geometry in occluded

Read original source ↗ Open in workspace

recordType

paper

region

Global