提出高效3D重建系统EGG-Fusion，提升实时性与精度。
EGG-Fusion: Efficient 3D Reconstruction with Geometry-aware Gaussian Surfel on the Fly
- 引入几何感知的可微高斯表元映射，融合多视角一致表面
- 在Replica和ScanNet++上实现0.6厘米误差，比现有方法高20%精度
- 支持24帧/秒实时运行，适合高精度动态场景重建
实时3D重建是计算机图形学中的基础任务。近年来，基于可微渲染的SLAM系统展现出巨大潜力，通过可学习的场景表示（如神经辐射场NeRF和3D高斯溅射3DGS）实现照片级真实感渲染。然而，现有可微渲染方法在实时计算与传感器噪声敏感性方面面临双重挑战，导致场景重建几何保真度下降，实用性受限。为此，我们提出一种新型实时系统EGG-Fusion，包含鲁棒的稀疏到稠密相机追踪与几何感知的高斯表元映射模块，采用基于信息滤波器的融合方法，显式建模传感器噪声，实现高精度表面重建。所提出的可微高斯表元映射有效建模多视角一致性表面，并支持高效参数优化。大量实验表明，该系统在Replica和ScanNet++等标准基准数据集上达到0.6厘米的表面重建误差，相较当前最优的基于GS的方法提升超过20%精度。值得注意的是，系统保持24帧/秒的实时处理能力，成为最精确的可微渲染类实时重建系统之一。
原文摘要 · Abstract (English)
Real-time 3D reconstruction is a fundamental task in computer graphics. Recently, differentiable-rendering-based SLAM system has demonstrated significant potential, enabling photorealistic scene rendering through learnable scene representations such as Neural Radiance Fields (NeRF) and 3D Gaussian Splatting (3DGS). Current differentiable rendering methods face dual challenges in real-time computation and sensor noise sensitivity, leading to degraded geometric fidelity in scene reconstruction and limited practicality. To address these challenges, we propose a novel real-time system EGG-Fusion, featuring robust sparse-to-dense camera tracking and a geometry-aware Gaussian surfel mapping module, introducing an information filter-based fusion method that explicitly accounts for sensor noise to achieve high-precision surface reconstruction. The proposed differentiable Gaussian surfel mapping effectively models multi-view consistent surfaces while enabling efficient parameter optimization. Extensive experimental results demonstrate that the proposed system achieves a surface reconstruction error of 0.6\textit{cm} on standardized benchmark datasets including Replica and ScanNet++, representing over 20\% improvement in accuracy compared to state-of-the-art (SOTA) GS-based methods. Notably, the system maintains real-time processing capabilities at 24 FPS, establishing it as one of the most accurate differentiable-rendering-based real-time reconstruction systems. Project Page: https://zju3dv.github.io/eggfusion/
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。