MegaParts：通过令牌高效自回归建模实现部件感知三维物体生成扩展至300个部件

摘要

部件感知的三维物体生成对于可控建模、编辑和关节化等图形应用至关重要，其中物体被表示为语义部件的连贯装配体。然而，现有的部件感知生成方法难以扩展到高度复杂的物体。随着部件数量的增加，生成精细几何体所需的 token 长度和内存开销变得高得难以承受。我们提出 MegaParts，一种可扩展的自回归三维生成框架，通过将结构化序列建模与 token 高效的向量量化形状分词器相结合来应对这一挑战。我们的分词器学习部件级几何的离散潜在表示，在高保真重建的约束下最小化 token 使用量，从而能够根据几何复杂度进行自适应长度的 token 化。在这一紧凑表示的基础上，我们训练一个大语言模型，在统一的结构化序列中生成物体包围盒、部件包围盒和部件形状 token。再结合高效的长上下文训练策略，我们这种 token 高效的表示可扩展到部件数量多达 300、序列长度高达 256k token 的物体。这大幅扩展了部件感知三维生成的规模，同时保留了组合结构并实现了细粒度的部件级控制。我们的方法在网格质量上优于基线自回归模型和扩散模型，表明压缩的离散部件 token 不仅提升了可扩展性，还提升了生成几何体可达到的保真度。这些结果表明，对于大规模部件感知三维生成，LLM 原生的 token 高效自回归建模是扩散模型的有力替代方案。项目页面可在 https://expmaster.github.io/megaparts_webpage 获取。

English

Part-aware 3D object generation is essential for graphics applications such as controllable modeling, editing, and articulation, where objects are represented as coherent assemblies of semantic parts. However, existing part-aware generation methods, do not scale well to highly complex objects. As the number of parts increases, generating detailed geometry becomes prohibitively expensive in token length and memory. We introduce MegaParts, a scalable autoregressive 3D generation framework to address this challenge by combining structured sequence modeling with a token-efficient vector-quantized shape tokenizer. Our tokenizer learns discrete latent representations for part-level geometry by minimizing token usage subject to high-fidelity reconstruction, enabling adaptive-length tokenization based on geometric complexity. On top of this compact representation, we train a large language model to generate object bounding boxes, part bounding boxes, and part shape tokens within a unified structured sequence. Combined with efficient long-context training strategy, our token-efficient formulation scales to objects with up to 300 parts and sequence lengths up to 256k tokens. This substantially extends the scale of part-aware 3D generation while preserving compositional structure and enabling fine-grained part-level control. Our method achieves higher mesh quality than baseline autoregressive and diffusion models, showing that compressed discrete part tokens improve not only scalability but also the achievable fidelity of generated geometry. These results suggest that LLM native token-efficient autoregressive modeling is a compelling alternative to diffusion for large-scale part-aware 3D generation. The project page is available at https://expmaster.github.io/megaparts_webpage.