ARMesh：通过下一细节层级预测的自回归网格生成
ARMesh: Autoregressive Mesh Generation via Next-Level-of-Detail Prediction
AI总结：
提出ARMesh，一种基于Transformer的自回归网格生成方法，通过按细节层级从粗到细地逆简化过程，实现渐进式网格构建，支持质量控制和网格编辑。
摘要：
直接生成3D网格（图形行业中3D形状的默认表示）已成为当今流行的做法，这得益于自回归（AR）模型在生成结果上的清晰性、紧凑性以及表示各种类型表面的能力。然而，AR网格生成模型通常按字典序逐面构建网格，这种方式不能以符合人类感知的方式有效捕捉底层几何结构。受二维模型中逐步细化图像的启发，例如流行的下一尺度预测AR模型，我们提出以渐进式从粗到细的方式自回归生成网格。具体来说，我们将网格简化算法（逐步合并网格面以构建更简单网格）视为自然的从细到粗过程。因此，我们将网格推广到单纯复形，并开发了一个基于Transformer的AR模型，以近似简化的逆过程，按细节层级顺序构建网格，最初从单个点开始，通过局部重新网格化逐步添加几何细节，其中拓扑不是预定义的且可以改变。我们的实验表明，这种新颖的渐进式网格生成方法不仅通过提前停止自回归过程提供了对生成质量和时间消耗的直观控制，还支持网格细化和编辑等应用。
英文摘要：
Directly generating 3D meshes, the default representation for 3D shapes in the graphics industry, using auto-regressive (AR) models has become popular these days, thanks to their sharpness, compactness in the generated results, and ability to represent various types of surfaces. However, AR mesh generative models typically construct meshes face by face in lexicographic order, which does not effectively capture the underlying geometry in a manner consistent with human perception. Inspired by 2D models that progressively refine images, such as the prevailing next-scale prediction AR models, we propose generating meshes auto-regressively in a progressive coarse-to-fine manner. Specifically, we view mesh simplification algorithms, which gradually merge mesh faces to build simpler meshes, as a natural fine-to-coarse process. Therefore, we generalize meshes to simplicial complexes and develop a transformer-based AR model to approximate the reverse process of simplification in the order of level of detail, constructing meshes initially from a single point and gradually adding geometric details through local remeshing, where the topology is not predefined and is alterable. Our experiments show that this novel progressive mesh generation approach not only provides intuitive control over generation quality and time consumption by early stopping the auto-regressive process but also enables applications such as mesh refinement and editing.
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。
