用可微渲染实现高质量网格重建，支持实时3D引擎交互
MeshSplatting: Differentiable Rendering with Opaque Meshes
- 基于网格的可微渲染，联合优化几何与外观
- 在Mip-NeRF360上比现有方法提升0.69dB PSNR
- 训练更快、内存更少，适合游戏与AR/VR应用
基于点的点阵方法（如3D高斯点阵）已推动新视角合成实现实时渲染，但其点状表示与驱动AR/VR及游戏引擎的网格管线不兼容。我们提出MeshSplatting，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。通过限制德劳内三角剖分保持连通性并优化表面一致性，生成端到端平滑、视觉质量高的网格，可在实时3D引擎中高效渲染。在Mip-NeRF360数据集上，相比当前最优网格方法MiLo，PSNR提升0.69 dB，训练速度提升2倍，内存使用减少2倍，弥合了神经渲染与交互式3D图形之间的鸿沟，支持无缝实时场景交互。
原文摘要 · Abstract (English)
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/.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。