CubePart: An Open-Vocabulary Part-Controllable 3D Generator

2026-05-27

AI Summary

Existing 3D generation models struggle to produce assets with well-defined semantic structures that can be directly deployed in interactive applications. This work proposes the first 3D mesh generation framework supporting open-vocabulary inputs and user-defined part structures, enabling explicit control over semantic composition during inference through text prompts and a part list. The method employs a two-stage architecture that decouples global shape synthesis from part-level decoding and introduces a text-to-part semantic alignment mechanism. Additionally, the authors curate a large-scale 3D dataset annotated with part labels. The resulting assets can be directly imported into game engines and readily support animation and scripting without any post-processing, significantly enhancing both controllability and practical utility.

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/

Problem

• part-controllable 3D generation
• semantic part decomposition
• open-vocabulary 3D modeling
• interactive 3D assets
• application-specific part structure

Innovation

• part-controllable generation
• open-vocabulary 3D generation
• semantic part decomposition
• two-stage generative architecture
• 3D asset creation