用极短令牌序列实现高保真3D重建，关键在分层信息前缀设计。
ZipTok3D: High-Fidelity 3D Tokenization with Compact Token Prefixes
- 通过嵌套丢弃训练，让前缀令牌聚焦核心几何信息。
- 仅需1个令牌（ShapeNet）或4个令牌（TRELLIS）达基线32倍/8倍压缩率。
- 适合低资源3D生成场景，如移动端部署或实时渲染。
紧凑的令牌序列对高效3D生成至关重要。然而，现有3D分词器通常将潜在表示组织为空间区域或固定大小的全局令牌集，当压缩至极低令牌预算时，重建质量急剧下降。本文提出ZipTok3D，一种专为极短令牌序列设计的3D分词器，可实现高保真重建。其核心思想是将物体几何组织为逐步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，在训练中使用嵌套丢弃随机截断编码后的潜在序列，要求每个保留的前缀都能重构完整物体，从而在前端令牌中优先保留关键几何信息。解码器则重复应用参数共享的Transformer模块，从每个前缀恢复细粒度几何，无需独立生成采样阶段。在相同令牌维度下，ZipTok3D在ShapeNet上仅用1个令牌即可达到与32令牌的COD-VAE基线相当的重建质量，在TRELLIS上仅需4个令牌，分别实现32倍和8倍的令牌序列压缩。
原文摘要 · Abstract (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 $32\times$ and $8\times$ shorter token sequences, respectively.
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。