Triangle meshes play a crucial role in 3D applications for efficient manipulation and rendering. While auto-regressive methods generate structured meshes by predicting discrete vertex tokens, they are often constrained by limited face counts and mesh incompleteness. To address these challenges, we propose DeepMesh, a framework that optimizes mesh generation through two key innovations: (1) an efficient pre-training strategy incorporating a novel tokenization algorithm, along with improvements in data curation and processing, and (2) the introduction of Reinforcement Learning (RL) into 3D mesh generation to achieve human preference alignment via Direct Preference Optimization (DPO). We design a scoring standard that combines human evaluation with 3D metrics to collect preference pairs for DPO, ensuring both visual appeal and geometric accuracy. Conditioned on point clouds and images, DeepMesh generates meshes with intricate details and precise topology, outperforming state-of-the-art methods in both precision and quality. Project page: https://zhaorw02.github.io/DeepMesh/

翻译：三角形网格在三维应用中对于高效操作与渲染起着至关重要的作用。尽管自回归方法通过预测离散顶点标记来生成结构化网格，但它们通常受限于有限的面片数量与网格不完整性。为应对这些挑战，我们提出了DeepMesh框架，该框架通过两项关键创新优化网格生成过程：（1）一种高效的预训练策略，融合了新颖的标记化算法，并改进了数据整理与处理流程；（2）将强化学习引入三维网格生成领域，通过直接偏好优化实现与人类偏好的对齐。我们设计了一套结合人类评估与三维几何指标的评分标准，用于收集DPO所需的偏好对数据，从而确保生成结果兼具视觉吸引力与几何精确性。在点云与图像的条件输入下，DeepMesh能够生成具有复杂细节与精确拓扑结构的网格，在精度与质量方面均超越了现有先进方法。项目页面：https://zhaorw02.github.io/DeepMesh/