拓扑雕刻器，形状精炼器：用于高保真3D网格生成的离散扩散模型
Topology Sculptor, Shape Refiner: Discrete Diffusion Model for High-Fidelity 3D Meshes Generation
AI总结：
本文提出TSSR，一种基于离散扩散模型的并行生成方法，通过解耦训练、改进沙漏架构和连接损失，生成高保真3D网格，支持1024^3分辨率下多达10000个面。
摘要：
在本文中，我们介绍了拓扑雕刻器，形状精炼器（TSSR），一种基于离散扩散模型（DDMs）生成高质量、艺术家风格3D网格的新方法。我们提出TSSR的主要动机是实现高度准确的令牌预测，同时支持并行生成，这是相对于顺序自回归方法的一大优势。通过让TSSR同时“看到”所有网格令牌，我们解锁了新的效率和可控性水平。我们通过三项关键创新来利用这种并行生成能力：1）解耦训练与混合推理，该方法将基于DDM的生成明确分为拓扑雕刻阶段和随后的形状精炼阶段。这种策略性解耦使TSSR能够有效捕捉复杂的局部拓扑和整体的全局形状。2）改进的沙漏架构，其特点是双向注意力，并通过面-顶点-序列级别的旋转位置嵌入（RoPE）增强，从而在网格结构中捕捉更丰富的上下文信息。3）一种新颖的连接损失，作为拓扑约束，进一步增强生成网格的真实感和保真度。在复杂数据集上的大量实验表明，TSSR能够生成高质量的3D艺术家风格网格，在$1024^3$的显著空间分辨率下，能够实现多达10,000个面。代码将在https://github.com/psky1111/Tencent-TSSR发布。
英文摘要：
In this paper, we introduce Topology Sculptor, Shape Refiner (TSSR), a novel method for generating high-quality, artist-style 3D meshes based on Discrete Diffusion Models (DDMs). Our primary motivation for TSSR is to achieve highly accurate token prediction while enabling parallel generation, a significant advantage over sequential autoregressive methods. By allowing TSSR to "see" all mesh tokens concurrently, we unlock a new level of efficiency and control. We leverage this parallel generation capability through three key innovations: 1) Decoupled Training and Hybrid Inference, which distinctly separates the DDM-based generation into a topology sculpting stage and a subsequent shape refinement stage. This strategic decoupling enables TSSR to effectively capture both intricate local topology and overarching global shape. 2) An Improved Hourglass Architecture, featuring bidirectional attention enriched by face-vertex-sequence level Rotational Positional Embeddings (RoPE), thereby capturing richer contextual information across the mesh structure. 3) A novel Connection Loss, which acts as a topological constraint to further enhance the realism and fidelity of the generated meshes. Extensive experiments on complex datasets demonstrate that TSSR generates high-quality 3D artist-style meshes, capable of achieving up to 10,000 faces at a remarkable spatial resolution of $1024^3$. The code will be released at: https://github.com/psky1111/Tencent-TSSR.
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。
