Volumetric Surfaces: Representing Fuzzy Geometries with Layered Meshes

TL;DR

This paper introduces a layered mesh representation for fuzzy geometries that enables real-time, sorting-free rendering with bounded sampling, improving efficiency and accuracy over traditional volume and surface rendering methods.

Contribution

The authors propose a novel multi-layer mesh approach that models fuzzy objects with bounded sampling and efficient rasterization, suitable for real-time view synthesis on low-power devices.

Findings

Achieves real-time rendering on low-power devices.

Models fuzzy geometries more accurately than single-surface methods.

Reduces computational overhead compared to volume rendering.

Abstract

High-quality view synthesis relies on volume rendering, splatting, or surface rendering. While surface rendering is typically the fastest, it struggles to accurately model fuzzy geometry like hair. In turn, alpha-blending techniques excel at representing fuzzy materials but require an unbounded number of samples per ray (P1). Further overheads are induced by empty space skipping in volume rendering (P2) and sorting input primitives in splatting (P3). We present a novel representation for real-time view synthesis where the (P1) number of sampling locations is small and bounded, (P2) sampling locations are efficiently found via rasterization, and (P3) rendering is sorting-free. We achieve this by representing objects as semi-transparent multi-layer meshes rendered in a fixed order. First, we model surface layers as signed distance function (SDF) shells with optimal spacing learned during training. Then, we bake them as meshes and fit UV textures. Unlike single-surface methods, our multi-layer representation effectively models fuzzy objects. In contrast to volume and splatting-based methods, our approach enables real-time rendering on low-power laptops and smartphones.