无需标注数据，自动学习3D形状的层级结构。
Hierarchical Transformers for Unsupervised 3D Shape Abstraction
- 用分层Transformer构建树状结构，通过压缩码本识别共性子结构。
- 在55类ShapeNet上实现多级无监督分割，层次结构由数据自适应推导。
- 不固定二叉等结构限制，可发现更复杂通用的层级关系，适合形状分析研究者。
我们提出HiT，一种新颖的分层神经场表示方法，用于在无监督设置下以粗到细的方式学习跨多种形状类别的通用层次结构。核心贡献是分层Transformer（HiT），其中每一层通过压缩码本学习树形层次中的父子关系。该码本使网络能够自动识别可能差异较大的形状类别间的共性子结构。与以往受限于固定层次结构（如二叉）的方法不同，我们的方法仅对每层节点总数进行限制，不施加其他约束。这种灵活性使得模型能直接从数据中推断出层次结构，适用于多类别形状，能表示比先前方法更普遍、更复杂的层次结构。在大规模重建损失训练下，模型成功捕捉了父节点与子节点间的有意义包含关系。我们在全部55个ShapeNet类别上验证了其有效性，实现了多级无监督形状分割。
原文摘要 · Abstract (English)
We introduce HiT, a novel hierarchical neural field representation for 3D shapes that learns general hierarchies in a coarse-to-fine manner across different shape categories in an unsupervised setting. Our key contribution is a hierarchical transformer (HiT), where each level learns parent-child relationships of the tree hierarchy using a compressed codebook. This codebook enables the network to automatically identify common substructures across potentially diverse shape categories. Unlike previous works that constrain the task to a fixed hierarchical structure (e.g., binary), we impose no such restriction, except for limiting the total number of nodes at each tree level. This flexibility allows our method to infer the hierarchical structure directly from data, over multiple shape categories, and representing more general and complex hierarchies than prior approaches. When trained at scale with a reconstruction loss, our model captures meaningful containment relationships between parent and child nodes. We demonstrate its effectiveness through an unsupervised shape segmentation task over all 55 ShapeNet categories, where our method successfully segments shapes into multiple levels of granularity.
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。