CubePart: An Open-Vocabulary Part-Controllable 3D Generator
Not on the map. Why?
Abstract (arXiv)
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/
Key facts. Cited by 5 papers in the map (data through 14 Oct 2026). Builds on 34 of its 68 references that are in the map. First posted on arXiv 27 May 2026.
Builds on
34 of 68 references.
References · 34
- 2023Segment Anythingcited by 8,234
- 2015ShapeNet: An Information-Rich 3D Model Repositorycited by 2,897
- 2022Objaverse: A Universe of Annotated 3D Objectscited by 1,540
- 2023Zero-1-to-3: Zero-shot One Image to 3D Objectcited by 1,489
- 2023ProlificDreamer: High-Fidelity and Diverse Text-to-3D Generation with Variational Score Distillationcited by 1,219
- 2023Objaverse-XL: A Universe of 10M+ 3D Objectscited by 774
- 2024Structured 3D Latents for Scalable and Versatile 3D Generationcited by 770
- 2024SiT: Exploring Flow and Diffusion-based Generative Models with Scalable Interpolant Transformerscited by 737
- 20233DShape2VecSet: A 3D Shape Representation for Neural Fields and Generative Diffusion Modelscited by 458
- 2024CLAY: A Controllable Large-scale Generative Model for Creating High-quality 3D Assetscited by 455
- 2022GET3D: A Generative Model of High Quality 3D Textured Shapes Learned from Imagescited by 446
- 2021ABO: Dataset and Benchmarks for Real-World 3D Object Understandingcited by 366
22 more
- 2023Michelangelo: Conditional 3D Shape Generation based on Shape-Image-Text Aligned Latent Representationcited by 228
- 2023XCube: Large-Scale 3D Generative Modeling using Sparse Voxel Hierarchiescited by 189
- 2025Hunyuan3D 2.1: From Images to High-Fidelity 3D Assets with Production-Ready PBR Materialcited by 165
- 2024CraftsMan3D: High-fidelity Mesh Generation with 3D Native Generation and Interactive Geometry Refinercited by 123
- 2025Direct3D-S2: Gigascale 3D Generation Made Easy with Spatial Sparse Attentioncited by 110
- 2025Step1X-3D: Towards High-Fidelity and Controllable Generation of Textured 3D Assetscited by 87
- 2025SparseFlex: High-Resolution and Arbitrary-Topology 3D Shape Modelingcited by 79
- 2023Alleviating Exposure Bias in Diffusion Models through Sampling with Shifted Time Stepscited by 73
- 2023SALAD: Part-Level Latent Diffusion for 3D Shape Generation and Manipulationcited by 66
- 2024PartGen: Part-level 3D Generation and Reconstruction with Multi-View Diffusion Modelscited by 62
- 2025OmniPart: Part-Aware 3D Generation with Semantic Decoupling and Structural Cohesioncited by 61
- 2025HoloPart: Generative 3D Part Amodal Segmentationcited by 60
- 2024ComboVerse: Compositional 3D Assets Creation Using Spatially-Aware Diffusion Guidancecited by 59
- 2024Part123: Part-aware 3D Reconstruction from a Single-view Imagecited by 55
- 2025Efficient Part-level 3D Object Generation via Dual Volume Packingcited by 48
- 2025X-Part: high fidelity and structure coherent shape decompositioncited by 44
- 2025LATTICE: Democratize High-Fidelity 3D Generation at Scalecited by 44
- 2025P3-SAM: Native 3D Part Segmentationcited by 43
- 2025BANG: Dividing 3D Assets via Generative Exploded Dynamicscited by 35
- 2022Neural Template: Topology-aware Reconstruction and Disentangled Generation of 3D Meshescited by 34
- 2025UniPart: Part-Level 3D Generation with Unified 3D Geom-Seg Latentscited by 9
- 2026PatchAlign3D: Local Feature Alignment for Dense 3D Shape Understandingcited by 6
Built on by
Citing papers per year: 2026: 5.
5 papers.
- 2026AI for Games in the Foundation Model Eracited by 3
- 2026Hunyuan3D-Buffalo 1.0: A Unified Multimodal Model for Scalable 3D Generation, Understanding, and Editingcited by 0
- 2026MultiCube: Compositional 3D Generation With Part-Level Semantic and Spatial Controlcited by 0
- 2026SNAP3D: Physically Grounded 3D Parts for Assembly from a Single Imagecited by 0
- 2026Point2Part: Unified 3D Partitioning from Point Promptscited by 0
- 2026Point2Part: Unified 3D Partitioning from Point Prompts29 Sep 2026
- 2026AI for Games in the Foundation Model Era15 Sep 2026
- 2026SNAP3D: Physically Grounded 3D Parts for Assembly from a Single Image11 Sep 2026
- 2026MultiCube: Compositional 3D Generation With Part-Level Semantic and Spatial Control20 Aug 2026
- 2026Hunyuan3D-Buffalo 1.0: A Unified Multimodal Model for Scalable 3D Generation, Understanding, and Editing3 Aug 2026