MeshAnything V2：藝術家創建的具有相鄰網格標記化的網格生成

MeshAnything V2: Artist-Created Mesh Generation With Adjacent Mesh Tokenization

August 5, 2024

作者: Yiwen Chen, Yikai Wang, Yihao Luo, Zhengyi Wang, Zilong Chen, Jun Zhu, Chi Zhang, Guosheng Lin

cs.AI

摘要

我們介紹了MeshAnything V2，這是一種自回歸變壓器，可生成與給定形狀對齊的藝術家創建的網格（AM）。它可以與各種3D資產生產流程集成，以實現高質量、高度可控的AM生成。MeshAnything V2在相同大小的模型下，效率和性能均超越先前的方法。這些改進是由於我們新提出的網格標記化方法：相鄰網格標記化（AMT）。與以往將每個面用三個頂點表示的方法不同，AMT在可能的情況下使用單個頂點。與以往的方法相比，AMT平均需要大約一半的標記序列長度來表示相同的網格。此外，來自AMT的標記序列更加緊湊且結構良好，從根本上有利於AM生成。我們的大量實驗表明，AMT顯著提高了AM生成的效率和性能。專案頁面：https://buaacyw.github.io/meshanything-v2/

English

We introduce MeshAnything V2, an autoregressive transformer that generates Artist-Created Meshes (AM) aligned to given shapes. It can be integrated with various 3D asset production pipelines to achieve high-quality, highly controllable AM generation. MeshAnything V2 surpasses previous methods in both efficiency and performance using models of the same size. These improvements are due to our newly proposed mesh tokenization method: Adjacent Mesh Tokenization (AMT). Different from previous methods that represent each face with three vertices, AMT uses a single vertex whenever possible. Compared to previous methods, AMT requires about half the token sequence length to represent the same mesh in average. Furthermore, the token sequences from AMT are more compact and well-structured, fundamentally benefiting AM generation. Our extensive experiments show that AMT significantly improves the efficiency and performance of AM generation. Project Page: https://buaacyw.github.io/meshanything-v2/