MeshSplatting：基于不透明网格的可微渲染
MeshSplatting: Differentiable Rendering with Opaque Meshes
把基于点的泼溅表示换成端到端可优化的连通网格，用受限 Delaunay 三角剖分约束拓扑、用可微渲染联合优化几何与外观，使神经渲染结果能直接进 AR/VR 与游戏引擎；做新视角合成或网格重建的人可借鉴其「泼溅式优化 + 网格输出」的管线。
原文依据 By enforcing connectivity via restricted Delaunay triangulation and refining surface consistency, Mesh Splatting creates end-to-end smooth, high-fidelity meshes
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论以 3D 高斯泼溅（3DGS）为代表的基于图元的泼溅方法凭借实时渲染能力革新了新视角合成。然而，其基于点的表示与支撑 AR/VR 和游戏引擎的网格管线仍不兼容。我们提出 Mesh Splatting，一种基于网格的重建方法，通过可微渲染联合优化几何与外观。借助受限 Delaunay 三角剖分施加连通性约束并精修表面一致性，Mesh Splatting 生成端到端平滑、高保真的网格，可在实时引擎中高效渲染。在 Mip-NeRF360 与 Tanks&Temples 上，它将峰值信噪比提升 +0.69dB，同时训练速度快 2 倍、内存占用少 2 倍，从而在神经渲染与交互式三维图形之间架起桥梁，实现无缝的实时场景交互。项目主页见 https://meshsplatting.github.io/。
英文原文摘要 885 字符
Primitive-based splatting methods like 3D Gaussian Splatting (3DGS) 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 Mesh Splatting, 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, Mesh Splatting creates end-to-end smooth, high-fidelity meshes that render efficiently in real-time engines. On Mip-NeRF360 and Tanks&Temples, it boosts PSNR by +0.69dB, 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/.