ZipTok3D：利用紧凑标记前缀的高保真3D标记化

摘要

紧凑的令牌序列对于高效的三维生成至关重要。然而，现有的三维令牌化器通常将潜在表示组织为空间区域形式或固定大小的全局令牌集合，这两者在压缩至极低令牌预算时都会出现严重的重建退化。在本文中，我们提出了ZipTok3D，一种专为从极短令牌序列中进行高保真重建而设计的三维令牌化器。其核心思想是将物体几何信息组织为逐步信息丰富的全局令牌前缀，并通过迭代解码展开这些紧凑表示。具体而言，嵌套丢弃法在编码后随机截断潜在序列，并要求每个保留的前缀都能重建出完整物体，从而将关键几何信息优先分配到前导令牌中。随后，解码器反复应用参数共享的Transformer模块，从每个前缀中恢复细粒度几何信息，而无需独立的生成式采样阶段。在相同令牌维度下，ZipTok3D在ShapeNet上仅需一个令牌即可达到与32令牌COD-VAE基线相当的重建质量，在TRELLIS上仅需四个令牌即可达到同等效果，分别使令牌序列缩短了32倍和8倍。

English

Compact token sequences are essential for efficient 3D generation. However, existing 3D tokenizers typically organize latent representations either over spatial regions or as fixed-size sets of global tokens, both suffering sharp reconstruction degradation when compressed to extremely low token budgets. In this paper, we present ZipTok3D, a 3D tokenizer designed for high-fidelity reconstruction from extremely short token sequences. Its key idea is to organize object geometry into progressively informative global-token prefixes and unfold these compact representations through iterative decoding. Specifically, nested dropout randomly truncates the latent sequence after encoding during training and requires each retained prefix to reconstruct the complete object, thereby prioritizing essential geometric information in the leading tokens. The decoder then repeatedly applies a parameter-shared Transformer block to recover fine-grained geometry from each prefix without a separate generative sampling stage. With the same token dimension, ZipTok3D achieves reconstruction quality comparable to the 32-token COD-VAE baseline using only one token on ShapeNet and four on TRELLIS, yielding 32times and 8times shorter token sequences, respectively.