Summary
WorldSculpt is a computer vision paper (arXiv:2609.05416) by Muyao Niu and colleagues addressing the generation of compositional 3D representations of heavily cluttered scenes containing hundreds of objects. The goal is to represent a scene as a collection of individual object meshes placed in a shared world frame, which is required by downstream applications such as gaming, AR/VR, simulation, and robotics. The task is challenging because dense occlusion means each camera view reveals only a fraction of object geometry. Geometry-based approaches reconstruct the scene as a single representation and leave incomplete geometry in occluded regions, while existing compositional methods using generative priors are limited to relatively simple scenes. The authors show that complex scenes with hundreds of objects can instead be generated compositionally, producing complete, individually manipulable object meshes within a coherent world coordinate system.
Paper Overview
Research Area: Computer Vision (CV)
Authors: Muyao Niu, Jixuan He, Ruihan Yu, Lian Fu, Yonghao Yu, Zheng-Hui Huang, Yifan Zhan, Fengbo Lan, Yongtao Ge, Yinqiang Zheng, Kaipeng Zhang, Zhixiang Wang
Published: 2026-09-04
arXiv: 2609.05416
Abstract
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 com- (excerpt truncated; see full paper on arXiv).
---
*Auto-collected on 2026-09-08.*
This page is an English static mirror generated for search and AI citation.
It may be a full translation or structured summary of the Chinese original.
Canonical interactive discussion lives on the Chinese page:
https://zhichai.net/topic/178634616