提升3D高斯点云渲染效果，更好表现金属等复杂反光。
Augmented Radiance Field: A General Framework for Enhanced Gaussian Splatting
- 用视角依赖的透明度显式建模镜面反射，改进颜色编码方式。
- 在真实场景中实现更高质量渲染，参数量比先进NeRF方法更少。
- 适用于需要高保真反射还原的工业级3D重建任务。
由于实时渲染性能优越，3D高斯点云（3DGS）已成为辐射场重建的主流方法。然而，其依赖球谐函数进行颜色编码，固有地限制了对漫反射与镜面反射的分离能力，难以准确表示复杂反射现象。为此，我们提出一种新型增强型高斯核，通过视角依赖的透明度显式建模镜面效应。同时引入误差驱动的补偿策略，提升现有3DGS场景的渲染质量。方法从2D高斯初始化开始，自适应插入并优化增强型高斯核，最终生成增强辐射场。实验表明，该方法在渲染性能上超越当前最优的NeRF方法，且具有更高的参数效率。项目页面：https://xiaoxinyyx.github.io/augs。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。