两篇新研究论文介绍了生成三维网格的先进方法，这是电影、游戏和交互式三维环境应用的关键组成部分。LATO.2 采用因子化流匹配框架，将顶点和拓扑生成分开，并以体素支架为锚点，能够生成更高分辨率的网格和进行拓扑自适应编辑。Nexus 利用扩散模型进行整体网格生成，通过基于八叉树的方法生成顶点，并使用新颖的时空间隔嵌入生成拓扑，从而将顶点和拓扑生成解耦，在实验和用户研究中表现优于现有方法。 AI
影响 这些方法通过提高网格生成的质量和效率，推动了三维内容创作的发展，可能对游戏、电影和虚拟现实等领域产生影响。
排序理由 两篇详细介绍三维网格生成新方法的独立研究论文。
在 Hugging Face Daily Papers 阅读 →
AI 生成摘要 · Google Gemini · 来自 5 个来源。 我们如何撰写摘要 →
完整方法见我们的编辑标准。
Generating high-quality triangle meshes is essential for film, gaming, and interactive 3D applications. Mainstream methods rely on mesh serialization and autoregressive processes, which stuggles in effective inference and is sensitive to error accumulation. In this paper, we pres…
Flow matching over carefully designed latent representations has recently emerged as a powerful paradigm for topology-aware mesh generation. Existing approaches, however, model vertices and connectivity jointly in a joint latent space, entangling continuous vertex geometry with d…
arXiv:2607.13563v1 Announce Type: new Abstract: Generating high-quality triangle meshes is essential for film, gaming, and interactive 3D applications. Mainstream methods rely on mesh serialization and autoregressive processes, which stuggles in effective inference and is sensiti…
Generating high-quality triangle meshes is essential for film, gaming, and interactive 3D applications. Mainstream methods rely on mesh serialization and autoregressive processes, which stuggles in effective inference and is sensitive to error accumulation. In this paper, we pres…
arXiv:2607.10623v1 Announce Type: cross Abstract: Flow matching over carefully designed latent representations has recently emerged as a powerful paradigm for topology-aware mesh generation. Existing approaches, however, model vertices and connectivity jointly in a joint latent s…