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

Victor Rong; Jan Held; Victor Chu; Daniel Rebain; Marc Van Droogenbroeck; Kiriakos N. Kutulakos; Andrea Tagliasacchi; David B. Lindell

Paper

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

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

fewer primitives and

less memory on outdoor scenes and using

fewer primitives and

less memory on indoor scenes. Our representation also renders twice as fast as existing textured primitives while improving upon their visual quality.