TreeMeshGPT：采用自回归树序列化的艺术化网格生成
TreeMeshGPT: Artistic Mesh Generation with Autoregressive Tree Sequencing
AI总结：
本文提出 TreeMeshGPT，通过基于三角形邻接的自回归树序列化和双 token 面表示，生成与点云对齐、细节精细且法线一致的高质量艺术网格。
摘要：
我们提出了 TreeMeshGPT，这是一种自回归 Transformer，旨在生成与输入点云对齐的高质量艺术化网格。不同于自回归 Transformer 中传统的下一 token 预测，我们提出了一种新颖的自回归树序列化（Autoregressive Tree Sequencing）：下一个输入 token 从动态增长的树结构中检索，而该树建立在网格内部各面的三角形邻接关系之上。我们的序列化使网格在每一步都能从最后生成的三角形面开始局部扩展，从而降低训练难度并提升网格质量。该方法用两个 token 表示每个三角形面，与朴素的面 token 化相比实现了约 22% 的压缩率。这种高效 token 化使模型能够在强点云条件约束下生成高度精细的艺术化网格，在能力和保真度上均超越以往方法。此外，该方法生成的网格具有强法线方向约束，最大限度减少了以往方法中常见的法线翻转问题。实验表明，TreeMeshGPT 以更精细的细节和法线方向一致性提升了网格生成质量。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
