用在线多视角立体视觉提升3D高斯点云建模质量
MVS-GS: High-Quality 3D Gaussian Splatting Mapping via Online Multi-View Stereo
- 通过局部时序帧估算多视角深度，实现精准初始化
- 融合深度优化与并行后端，显著提升重建细节与速度
- 适合需要高质量实时3D建模的户外场景应用
本研究针对基于RGB图像流的神经渲染在线3D建模挑战，提出一种基于在线多视图立体（MVS）的高质量3D高斯点云（3DGS）建模框架。现有方法多采用神经辐射场（NeRF）或3DGS作为场景表示，嵌入稠密SLAM中，但主要关注粗粒度场景估计，难以实现精细重建。仅依赖图像的深度估计常存在歧义，导致3D模型质量差、渲染不准确。为此，本方法利用局部时间窗口内的连续帧进行MVS深度估计，并结合多阶段深度优化技术剔除异常值，实现3DGS中高斯分布的精确初始化。同时引入并行化后端模块，高效优化3DGS模型，确保每新增关键帧即可及时更新。实验表明，该方法在复杂户外环境下优于当前最先进稠密SLAM方法，尤其在细节还原与渲染质量上表现突出。
原文摘要 · Abstract (English)
This study addresses the challenge of online 3D model generation for neural rendering using an RGB image stream. Previous research has tackled this issue by incorporating Neural Radiance Fields (NeRF) or 3D Gaussian Splatting (3DGS) as scene representations within dense SLAM methods. However, most studies focus primarily on estimating coarse 3D scenes rather than achieving detailed reconstructions. Moreover, depth estimation based solely on images is often ambiguous, resulting in low-quality 3D models that lead to inaccurate renderings. To overcome these limitations, we propose a novel framework for high-quality 3DGS modeling that leverages an online multi-view stereo (MVS) approach. Our method estimates MVS depth using sequential frames from a local time window and applies comprehensive depth refinement techniques to filter out outliers, enabling accurate initialization of Gaussians in 3DGS. Furthermore, we introduce a parallelized backend module that optimizes the 3DGS model efficiently, ensuring timely updates with each new keyframe. Experimental results demonstrate that our method outperforms state-of-the-art dense SLAM methods, particularly excelling in challenging outdoor environments.
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。