Nexels: Neurally-Textured Surfels for Real-Time Novel View Synthesis with Sparse Geometries

TL;DR

This paper introduces Nexels, a novel surfel-based representation for real-time view synthesis that significantly reduces memory and primitive count while maintaining high visual quality and rendering speed.

Contribution

Nexels decouples geometry and appearance using surfels and neural textures, achieving compactness and efficiency in novel view synthesis.

Findings

Matches perceptual quality of Gaussian splatting

Uses 9.7x fewer primitives on outdoor scenes

Renders twice as fast as existing methods

Abstract

Though Gaussian splatting has achieved impressive results in novel view synthesis, it requires millions of primitives to model highly textured scenes, even when the geometry of the scene is simple. We propose a representation that goes beyond point-based rendering and decouples geometry and appearance in order to achieve a compact representation. We use surfels for geometry and a combination of a global neural field and per-primitive colours for appearance. The neural field textures a fixed number of primitives for each pixel, ensuring that the added compute is low. Our representation matches the perceptual quality of 3D Gaussian splatting while using $9.7\times$ fewer primitives and $5.5\times$ less memory on outdoor scenes and using $31\times$ fewer primitives and $3.7\times$ less memory on indoor scenes. Our representation also renders twice as fast as existing textured primitives while improving upon their visual quality.