Search papers, labs, and topics across Lattice.
WorldSculpt recovers compositional, object-level 3D mesh representations of densely cluttered scenes containing hundreds of occluded objects directly from posed video observations. Rather than relying on monolithic scene representations or scarce multi-object training data, the method extends a single-object generative prior (Pixal3D) with a multi-view conditioning pathway trained strictly on isolated objects in canonical space. Evaluated on the new UE-MeshyScene benchmark, it significantly outperforms prior geometry- and prior-based baselines under severe occlusion while enabling the direct conversion of monolithic 3D Gaussian Splatting worlds into editable, simulator-ready assets.
Monolithic 3D scenes with hundreds of heavily occluded objects can be cleanly parsed into individual editable meshes without ever training on multi-object data.
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 regions, while existing compositional methods with generative priors are largely limited to relatively simple scenes. We show that complex scenes with hundreds of objects can instead be generated compositionally by adapting a strong single-object 3D generative prior to multi-view observations. We instantiate this paradigm with Pixal3D, extending it with a multi-view conditioning pathway that grounds object generation in multiple posed observations. Although the model is finetuned entirely on single objects in canonical space, it generalizes to large scenes with severe occlusion without any scene-level training, demonstrating the feasibility and scalability of this paradigm. We further introduce UE-MeshyScene, a photorealistic benchmark of densely cluttered scenes with hundreds of objects, per-object annotations, and ground-truth meshes. Across single-object, controlled multi-object, and UE-MeshyScene evaluations, our method consistently outperforms prior approaches, with larger gains as scene complexity and occlusion increase. Finally, we demonstrate broader applicability by converting generated 3DGS worlds, such as Marble and HY-World 2.0, into compositional mesh scenes.
