CubePart: An Open-Vocabulary Part-Controllable 3D Generator
2026-05-27 • Artificial Intelligence
Artificial Intelligence
AI summaryⓘ
The authors developed CubePart, a system that helps create 3D models made of different named parts based on text descriptions. Unlike normal 3D models that are single pieces or have random parts, CubePart generates each part separately according to user-defined names and combines them into a complete object. They built a large dataset of 3D shapes labeled with many part types and designed a two-step model to first create the overall shape and then the parts. This makes it easier to use the models directly in games and simulations where parts need to move or behave independently.
3D meshsemantic partsgenerative modelpart decompositiontext promptshape synthesisdatasetgame engine integrationanimationbehavior scripts
Authors
Yiheng Zhu, Kangle Deng, Jean-Philippe Fauconnier, Inaki Navarro, Daiqing Li, Ava Pun, Yinan Zhang, Peiye Zhuang, Xiaoxia Sun, Maneesh Agrawala, Kiran Bhat, Tinghui Zhou
Abstract
Interactive 3D assets used in games and simulation are typically decomposed into specific semantic parts to support animation, physics, and scripted behaviors, yet most generative 3D models produce either monolithic meshes or arbitrary part decompositions that cannot be aligned with application-specific requirements. We present CubePart, a generative framework for open-vocabulary, part-controllable 3D mesh generation that exposes part structure as an explicit inference-time control signal. Given a global text prompt and a user-defined parts schema expressed as an open-ended list of part names, our method generates a set of meshes - one per schema element - that assemble into a coherent object while respecting the specified semantic structure. To enable this capability, we introduce a scalable data pipeline to construct a large open-vocabulary, part-labeled 3D dataset, along with a two-stage generative architecture that separates global shape synthesis from part-level decoding. We demonstrate that the resulting assets can be directly integrated into game engines and driven by animation and behavior scripts without manual post-processing. Project Page: https://cubepart.github.io/