Augmented Radiance Field: A General Framework for Enhanced Gaussian Splatting

TL;DR

This paper introduces an augmented radiance field framework that enhances 3D Gaussian Splatting by explicitly modeling specular effects and improving rendering quality, leading to better performance and efficiency.

Contribution

It proposes a novel enhanced Gaussian kernel with view-dependent opacity and an error-driven compensation strategy for improved 3D Gaussian Splatting.

Findings

Outperforms state-of-the-art NeRF methods in rendering quality

Achieves greater parameter efficiency

Enhances representation of complex reflections

Abstract

Due to the real-time rendering performance, 3D Gaussian Splatting (3DGS) has emerged as the leading method for radiance field reconstruction. However, its reliance on spherical harmonics for color encoding inherently limits its ability to separate diffuse and specular components, making it challenging to accurately represent complex reflections. To address this, we propose a novel enhanced Gaussian kernel that explicitly models specular effects through view-dependent opacity. Meanwhile, we introduce an error-driven compensation strategy to improve rendering quality in existing 3DGS scenes. Our method begins with 2D Gaussian initialization and then adaptively inserts and optimizes enhanced Gaussian kernels, ultimately producing an augmented radiance field. Experiments demonstrate that our method not only surpasses state-of-the-art NeRF methods in rendering performance but also achieves greater parameter efficiency. Project page at: https://xiaoxinyyx.github.io/augs.