LoST：面向三维形状的语义层级标记化方法

摘要

分词技术是多模态生成建模中的基础方法，尤其在近期成为三维生成领域重要解决方案的自回归模型中具有关键作用。然而，三维形状的最优分词仍是悬而未决的难题。当前最先进方法主要依赖最初为渲染和压缩设计的几何细节层次结构，这类空间层次结构往往存在分词效率低下且缺乏自回归建模所需语义一致性的问题。我们提出语义层次分词法（LoST），该方法依据语义显著度对分词进行排序，使得早期前缀能解码出具备主体语义的完整合理形状，而后续分词则用于细化实例特有的几何与语义细节。为训练LoST，我们引入关系间距对齐（RIDA）这一新型三维语义对齐损失函数，通过对齐三维形状潜空间与语义DINO特征空间的关系结构实现语义对齐。实验表明，LoST在重建任务中达到最优水平，在几何与语义重建指标上均大幅超越基于细节层次的现有三维形状分词器。此外，LoST仅需先前自回归模型0.1%-10%的分词量，即可实现高效高质量的自回归三维生成，并支持语义检索等下游任务。

English

Tokenization is a fundamental technique in the generative modeling of various modalities. In particular, it plays a critical role in autoregressive (AR) models, which have recently emerged as a compelling option for 3D generation. However, optimal tokenization of 3D shapes remains an open question. State-of-the-art (SOTA) methods primarily rely on geometric level-of-detail (LoD) hierarchies, originally designed for rendering and compression. These spatial hierarchies are often token-inefficient and lack semantic coherence for AR modeling. We propose Level-of-Semantics Tokenization (LoST), which orders tokens by semantic salience, such that early prefixes decode into complete, plausible shapes that possess principal semantics, while subsequent tokens refine instance-specific geometric and semantic details. To train LoST, we introduce Relational Inter-Distance Alignment (RIDA), a novel 3D semantic alignment loss that aligns the relational structure of the 3D shape latent space with that of the semantic DINO feature space. Experiments show that LoST achieves SOTA reconstruction, surpassing previous LoD-based 3D shape tokenizers by large margins on both geometric and semantic reconstruction metrics. Moreover, LoST achieves efficient, high-quality AR 3D generation and enables downstream tasks like semantic retrieval, while using only 0.1%-10% of the tokens needed by prior AR models.

LoST：面向三维形状的语义层级标记化方法

LoST: Level of Semantics Tokenization for 3D Shapes

摘要

Support