ZipTok3D: High-Fidelity 3D Tokenization with Compact Token Prefixes

2026-09-01

AI Summary

本文提出ZipTok3D方法，通过紧凑的token前缀和迭代解码解决3D生成中因压缩导致的重建质量下降问题。

Abstract

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.

Problem

• 3D Tokenization
• Reconstruction Quality
• Token Budgets
• Compact Representations

Innovation

• Nested Dropout
• Progressively Informative Global-Token Prefixes
• Iterative Decoding
• Parameter-Shared Transformer Block