Enregistré dans:
Détails bibliographiques
Auteurs principaux: Held, Jan, Son, Sanghyun, Vandeghen, Renaud, Rebain, Daniel, Gadelha, Matheus, Zhou, Yi, Cioppa, Anthony, Lin, Ming C., Van Droogenbroeck, Marc, Tagliasacchi, Andrea
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:https://arxiv.org/abs/2512.06818
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866909947843837952
author Held, Jan
Son, Sanghyun
Vandeghen, Renaud
Rebain, Daniel
Gadelha, Matheus
Zhou, Yi
Cioppa, Anthony
Lin, Ming C.
Van Droogenbroeck, Marc
Tagliasacchi, Andrea
author_facet Held, Jan
Son, Sanghyun
Vandeghen, Renaud
Rebain, Daniel
Gadelha, Matheus
Zhou, Yi
Cioppa, Anthony
Lin, Ming C.
Van Droogenbroeck, Marc
Tagliasacchi, Andrea
contents 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/.
format Preprint
id arxiv_https___arxiv_org_abs_2512_06818
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle MeshSplatting: Differentiable Rendering with Opaque Meshes
Held, Jan
Son, Sanghyun
Vandeghen, Renaud
Rebain, Daniel
Gadelha, Matheus
Zhou, Yi
Cioppa, Anthony
Lin, Ming C.
Van Droogenbroeck, Marc
Tagliasacchi, Andrea
Computer Vision and Pattern Recognition
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/.
title MeshSplatting: Differentiable Rendering with Opaque Meshes
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2512.06818