用高斯体素核函数实现开放场景高效高保真三维重建
GVKF: Gaussian Voxel Kernel Functions for Highly Efficient Surface Reconstruction in Open Scenes
- 通过核回归将离散高斯点云转化为连续场景表示
- 实现实时渲染，存储与训练内存消耗大幅降低
- 适合需要快速重建且对细节要求高的开放场景应用
本文提出一种新型方法——高斯体素核函数（GVKF），用于开放场景中高效且高质量的三维表面重建。现有基于神经辐射场（NeRF）的方法因采用隐式表示，通常需要大量训练和渲染时间；而3D高斯泼溅（3DGS）虽采用显式离散表示，但依赖海量高斯原语，导致内存占用过高且稀疏区域表面细节粗糙。GVKF通过核回归在离散3DGS基础上构建连续场景表示，融合快速3DGS光栅化与高效隐式表达，实现高保真开放场景重建。在多个挑战性场景数据集上的实验表明，该方法兼具高质量重建、实时渲染速度，以及显著降低的存储与训练内存开销。
原文摘要 · Abstract (English)
In this paper we present a novel method for efficient and effective 3D surface reconstruction in open scenes. Existing Neural Radiance Fields (NeRF) based works typically require extensive training and rendering time due to the adopted implicit representations. In contrast, 3D Gaussian splatting (3DGS) uses an explicit and discrete representation, hence the reconstructed surface is built by the huge number of Gaussian primitives, which leads to excessive memory consumption and rough surface details in sparse Gaussian areas. To address these issues, we propose Gaussian Voxel Kernel Functions (GVKF), which establish a continuous scene representation based on discrete 3DGS through kernel regression. The GVKF integrates fast 3DGS rasterization and highly effective scene implicit representations, achieving high-fidelity open scene surface reconstruction. Experiments on challenging scene datasets demonstrate the efficiency and effectiveness of our proposed GVKF, featuring with high reconstruction quality, real-time rendering speed, significant savings in storage and training memory consumption.
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。