TreeMeshGPT：基於自迴歸樹序列的藝術化網格生成

TreeMeshGPT: Artistic Mesh Generation with Autoregressive Tree Sequencing

March 14, 2025

作者: Stefan Lionar, Jiabin Liang, Gim Hee Lee

cs.AI

摘要

我們介紹了TreeMeshGPT，這是一種自回歸Transformer，旨在生成與輸入點雲對齊的高質量藝術網格。與傳統自回歸Transformer中的下一個令牌預測不同，我們提出了一種新穎的自回歸樹序列化方法，其中下一個輸入令牌是從一個動態增長的樹結構中檢索的，該樹結構基於網格內面的三角形鄰接關係構建。我們的序列化方法使得網格能夠在每一步從最後生成的三角形面局部擴展，從而降低了訓練難度並提高了網格質量。我們的方法用兩個令牌表示每個三角形面，與簡單的面令牌化相比，實現了約22%的壓縮率。這種高效的令牌化使我們的模型能夠生成具有強點雲條件的高度詳細的藝術網格，在容量和保真度方面均超越了先前的方法。此外，我們的方法生成的網格具有強的法線方向約束，最大限度地減少了先前方法中常見的法線翻轉問題。我們的實驗表明，TreeMeshGPT通過精細的細節和法線方向一致性提升了網格生成質量。

English

We introduce TreeMeshGPT, an autoregressive Transformer designed to generate high-quality artistic meshes aligned with input point clouds. Instead of the conventional next-token prediction in autoregressive Transformer, we propose a novel Autoregressive Tree Sequencing where the next input token is retrieved from a dynamically growing tree structure that is built upon the triangle adjacency of faces within the mesh. Our sequencing enables the mesh to extend locally from the last generated triangular face at each step, and therefore reduces training difficulty and improves mesh quality. Our approach represents each triangular face with two tokens, achieving a compression rate of approximately 22% compared to the naive face tokenization. This efficient tokenization enables our model to generate highly detailed artistic meshes with strong point cloud conditioning, surpassing previous methods in both capacity and fidelity. Furthermore, our method generates mesh with strong normal orientation constraints, minimizing flipped normals commonly encountered in previous methods. Our experiments show that TreeMeshGPT enhances the mesh generation quality with refined details and normal orientation consistency.