MeshSplatting: Differentiable Rendering with Opaque Meshes
Jan Held, Sanghyun Son, Renaud Vandeghen, Daniel Rebain, Matheus Gadelha, Yi Zhou, Anthony Cioppa, Ming C. Lin
Abstract
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/.
BibTeX
@inproceedings{cvpr2026_meshsplattingdif,
title = {MeshSplatting: Differentiable Rendering with Opaque Meshes},
author = {Jan Held and Sanghyun Son and Renaud Vandeghen and Daniel Rebain and Matheus Gadelha and Yi Zhou and Anthony Cioppa and Ming C. Lin and Marc Van Droogenbroeck and Andrea Tagliasacchi},
booktitle = {CVPR 2026},
year = {2026}
}