用图结构生成更复杂的乐高搭建序列，突破传统积木堆叠限制。
BrickNet: Graph-Backed Generative Brick Assembly
- 用图结构建模积木连接关系，提升生成序列的物理合理性。
- 基于超10万件人类设计的乐高作品构建数据集，覆盖上千种零件。
- 适合对3D生成、具身智能或可组装设计感兴趣的开发者和研究者。
我们训练一个语言模型来生成乐高积木的搭建序列。与以往仅限于离散体素式塔楼的研究不同，本文考虑了更广泛的积木类型，涵盖数千种零件及其多样的连接语义。为实现这一目标，我们首先收集了一个大规模数据集，包含超过10万件由人类设计的LDraw积木物体和场景。由于设定复杂，自回归地构建满足物理约束的结构极具挑战性；直接预测积木位姿时，序列在少数步骤后即失效。尽管积木位于三维空间中，但整体结构由零件间的空间关系决定。为此，我们设计了一种基于图的程序表示法，通过连接性参数化结构，增强了生成序列的物理基础。为支持未来应用，我们已公开该数据集与模型以供研究使用。
原文摘要 · Abstract (English)
We train a language model to generate LEGO-brick build sequences. While prior work has been restricted to discrete, voxel-like towers, we consider a much broader set of pieces, encompassing thousands of part types with diverse connection semantics. To enable this, we first collect a large-scale dataset of over 100,000 human-designed LDraw brick objects and scenes. The complexity of our setting makes it challenging to autoregressively assemble structures that satisfy physical constraints. When predicting block pose directly, build sequences quickly become invalid after a small number of steps. Although pieces are placed in 3D space, it is the spatial relationships of the parts which define the whole. With this in mind, we design a graph-based program representation that parametrizes structure through connectivity, improving the physical grounding of generated sequences. To enable future applications, we make our dataset and models available for research purposes. https://kulits.github.io/BrickNet
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。