ZipTok3D: High-Fidelity 3D Tokenization with Compact Token Prefixes
This story is from 2026-09-03. It is preserved in the archive; the latest stories are on the live feed.
arXiv:2609.01740v1 Announce Type: new 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 degrad…
Read the full story at arXiv cs.CV ↗
Timeline · 1 report
- 2026-09-03 04:00 · arXiv cs.CV
ZipTok3D: High-Fidelity 3D Tokenization with Compact Token Prefixes