FreeMesh: Boosting Mesh Generation with Coordinates Merging

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Liu, Jian, Weng, Haohan, Lei, Biwen, Yang, Xianghui, Zhao, Zibo, Chen, Zhuo, Guo, Song, Han, Tao, Guo, Chunchao
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910955137400832
author Liu, Jian
Weng, Haohan
Lei, Biwen
Yang, Xianghui
Zhao, Zibo
Chen, Zhuo
Guo, Song
Han, Tao
Guo, Chunchao
author_facet Liu, Jian
Weng, Haohan
Lei, Biwen
Yang, Xianghui
Zhao, Zibo
Chen, Zhuo
Guo, Song
Han, Tao
Guo, Chunchao
contents The next-coordinate prediction paradigm has emerged as the de facto standard in current auto-regressive mesh generation methods. Despite their effectiveness, there is no efficient measurement for the various tokenizers that serialize meshes into sequences. In this paper, we introduce a new metric Per-Token-Mesh-Entropy (PTME) to evaluate the existing mesh tokenizers theoretically without any training. Building upon PTME, we propose a plug-and-play tokenization technique called coordinate merging. It further improves the compression ratios of existing tokenizers by rearranging and merging the most frequent patterns of coordinates. Through experiments on various tokenization methods like MeshXL, MeshAnything V2, and Edgerunner, we further validate the performance of our method. We hope that the proposed PTME and coordinate merging can enhance the existing mesh tokenizers and guide the further development of native mesh generation.
format Preprint
id arxiv_https___arxiv_org_abs_2505_13573
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle FreeMesh: Boosting Mesh Generation with Coordinates Merging
Liu, Jian
Weng, Haohan
Lei, Biwen
Yang, Xianghui
Zhao, Zibo
Chen, Zhuo
Guo, Song
Han, Tao
Guo, Chunchao
Graphics
Artificial Intelligence
The next-coordinate prediction paradigm has emerged as the de facto standard in current auto-regressive mesh generation methods. Despite their effectiveness, there is no efficient measurement for the various tokenizers that serialize meshes into sequences. In this paper, we introduce a new metric Per-Token-Mesh-Entropy (PTME) to evaluate the existing mesh tokenizers theoretically without any training. Building upon PTME, we propose a plug-and-play tokenization technique called coordinate merging. It further improves the compression ratios of existing tokenizers by rearranging and merging the most frequent patterns of coordinates. Through experiments on various tokenization methods like MeshXL, MeshAnything V2, and Edgerunner, we further validate the performance of our method. We hope that the proposed PTME and coordinate merging can enhance the existing mesh tokenizers and guide the further development of native mesh generation.
title FreeMesh: Boosting Mesh Generation with Coordinates Merging
topic Graphics
Artificial Intelligence
url https://arxiv.org/abs/2505.13573