基于网格的可微渲染：使用不透明网格的可微渲染
MeshSplatting: Differentiable Rendering with Opaque Meshes
AI总结：
MeshSplatting通过可微渲染方法，实现了基于网格的高效重建，提升了实时3D场景交互的质量和性能。
摘要：
基于原始的溅射方法，如3D高斯溅射，已经通过实时渲染革新了新型视角合成。然而，其点表示仍然无法与驱动AR/VR和游戏引擎的网格基于管道兼容。我们提出了MeshSplatting，一种基于网格的重建方法，通过可微渲染联合优化几何和外观。通过通过限制的德劳内三角化强制连接，并通过细化表面一致性，MeshSplatting创建了端到端平滑、视觉高质量的网格，可以在实时3D引擎中高效渲染。在Mip-NeRF360上，它在当前最先进的MiLo基础上将PSNR提高了+0.69 dB，同时训练速度快2倍，内存使用少2倍，弥合了神经渲染与交互式3D图形之间的差距，为无缝的实时场景交互提供了可能。项目页面可在https://meshsplatting.github.io/上访问。
英文摘要：
Primitive-based splatting methods like 3D Gaussian Splatting have revolutionized novel view synthesis with real-time rendering. However, their point-based representations remain incompatible with mesh-based pipelines that power AR/VR and game engines. We present MeshSplatting, a mesh-based reconstruction approach that jointly optimizes geometry and appearance through differentiable rendering. By enforcing connectivity via restricted Delaunay triangulation and refining surface consistency, MeshSplatting creates end-to-end smooth, visually high-quality meshes that render efficiently in real-time 3D engines. On Mip-NeRF360, it boosts PSNR by +0.69 dB over the current state-of-the-art MiLo for mesh-based novel view synthesis, while training 2x faster and using 2x less memory, bridging neural rendering and interactive 3D graphics for seamless real-time scene interaction. The project page is available at https://meshsplatting.github.io/.
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。
