Radiance Meshes for Volumetric Reconstruction
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914178980118528 |
|---|---|
| author | Mai, Alexander Hedstrom, Trevor Kopanas, George Kontkanen, Janne Kuester, Falko Barron, Jonathan T. |
| author_facet | Mai, Alexander Hedstrom, Trevor Kopanas, George Kontkanen, Janne Kuester, Falko Barron, Jonathan T. |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_04076 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Radiance Meshes for Volumetric Reconstruction Mai, Alexander Hedstrom, Trevor Kopanas, George Kontkanen, Janne Kuester, Falko Barron, Jonathan T. Graphics Computer Vision and Pattern Recognition I.4 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. |
| title | Radiance Meshes for Volumetric Reconstruction |
| topic | Graphics Computer Vision and Pattern Recognition I.4 |
| url | https://arxiv.org/abs/2512.04076 |