English

Radiance Meshes for Volumetric Reconstruction

Graphics 2025-12-04 v1 Computer Vision and Pattern Recognition

Abstract

We introduce radiance meshes, a technique for representing radiance fields with constant density tetrahedral cells produced with a Delaunay tetrahedralization. Unlike a Voronoi diagram, a Delaunay tetrahedralization yields simple triangles that are natively supported by existing hardware. As such, our model is able to perform exact and fast volume rendering using both rasterization and ray-tracing. We introduce a new rasterization method that achieves faster rendering speeds than all prior radiance field representations (assuming an equivalent number of primitives and resolution) across a variety of platforms. Optimizing the positions of Delaunay vertices introduces topological discontinuities (edge flips). To solve this, we use a Zip-NeRF-style backbone which allows us to express a smoothly varying field even when the topology changes. Our rendering method exactly evaluates the volume rendering equation and enables high quality, real-time view synthesis on standard consumer hardware. Our tetrahedral meshes also lend themselves to a variety of exciting applications including fisheye lens distortion, physics-based simulation, editing, and mesh extraction.

Keywords

Cite

@article{arxiv.2512.04076,
  title  = {Radiance Meshes for Volumetric Reconstruction},
  author = {Alexander Mai and Trevor Hedstrom and George Kopanas and Janne Kontkanen and Falko Kuester and Jonathan T. Barron},
  journal= {arXiv preprint arXiv:2512.04076},
  year   = {2025}
}

Comments

Website: half-potato.gitlab.io/rm

R2 v1 2026-07-01T08:08:12.949Z