FastMesh: 通过组件解耦实现高效的艺术网格生成
FastMesh: Efficient Artistic Mesh Generation via Component Decoupling
AI总结：
FastMesh 通过组件解耦高效生成艺术网格，采用自回归模型生成顶点并利用双向变压器完成网格，显著提升生成速度和质量。
摘要：
最近的网格生成方法通常将三角网格 tokenize 成 token 序列，并训练自回归模型来依次生成这些 token。尽管取得了显著进展，但此类 token 序列不可避免地会多次重复使用顶点，以完整表示流形网格，因为每个顶点被多个面共享。这种冗余导致 token 序列过长且生成过程低效。在本文中，我们提出了一种高效的框架，通过将顶点和面分开处理，显著减少了冗余。我们采用自回归模型仅用于生成顶点，将 token 数量减少到最紧凑现有 tokenizer 所需的约 23%。接下来，我们利用双向变压器在单步中完成网格，通过捕捉顶点间关系并构建定义网格面的邻接矩阵。为进一步提高生成质量，我们引入了保真度增强器，将顶点位置细化为更自然的排列，并提出了一种后处理框架以去除不受欢迎的边连接。实验结果表明，我们的方法在网格生成速度上比最先进的方法快了 8 倍以上，同时生成的网格质量更高。
英文摘要：
Recent mesh generation approaches typically tokenize triangle meshes into sequences of tokens and train autoregressive models to generate these tokens sequentially. Despite substantial progress, such token sequences inevitably reuse vertices multiple times to fully represent manifold meshes, as each vertex is shared by multiple faces. This redundancy leads to excessively long token sequences and inefficient generation processes. In this paper, we propose an efficient framework that generates artistic meshes by treating vertices and faces separately, significantly reducing redundancy. We employ an autoregressive model solely for vertex generation, decreasing the token count to approximately 23% of that required by the most compact existing tokenizer. Next, we leverage a bidirectional transformer to complete the mesh in a single step by capturing inter-vertex relationships and constructing the adjacency matrix that defines the mesh faces. To further improve the generation quality, we introduce a fidelity enhancer to refine vertex positioning into more natural arrangements and propose a post-processing framework to remove undesirable edge connections. Experimental results show that our method achieves more than 8x faster speed on mesh generation compared to state-of-the-art approaches, while producing higher mesh quality.
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。
