分离顶点与面的生成，让艺术网格生成快8倍且更精细。
FastMesh: Efficient Artistic Mesh Generation via Component Decoupling
- 先用自回归模型生成顶点，再一步构建面，减少冗余。
- 顶点序列仅需现有方法23%长度，生成速度提升超8倍。
- 适合需要高效高质量网格生成的艺术家和游戏开发者。
近期网格生成方法通常将三角网格切分为词元序列，并训练自回归模型逐个生成。然而，由于每个顶点被多个面共享，此类词元序列不可避免地重复使用顶点，导致序列过长、生成效率低下。本文提出一种高效框架，通过分别处理顶点与面来显著降低冗余。我们仅用自回归模型生成顶点，使词元数量降至现有最紧凑分词器的约23%。随后，利用双向Transformer在单步内完成网格构建，捕捉顶点间关系并生成定义网格面的邻接矩阵。为进一步提升质量，引入保真度增强模块优化顶点位置，并设计后处理框架移除不良边连接。实验表明，本方法在网格生成速度上比当前最优方法快逾8倍，同时生成质量更高。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。