Radiance Meshes for Volumetric Reconstruction

TL;DR

This paper presents radiance meshes, a novel volumetric representation using Delaunay tetrahedralization that enables fast, high-quality, real-time rendering on consumer hardware, with applications in editing and simulation.

Contribution

The paper introduces radiance meshes with a new rasterization method and a topology-aware optimization approach for efficient volumetric rendering.

Findings

Faster rendering speeds than prior radiance field methods.

Supports high-quality real-time view synthesis on consumer hardware.

Versatile applications including fisheye distortion and physics-based simulation.

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.