VDGS：面向航空场景重建的可见性驱动大规模3D高斯泼溅
VDGS: Visibility-Driven Large-Scale 3D Gaussian Splatting for Aerial Scene Reconstruction
浏览论文内容
中文总结 AI 辅助
提出VDGS框架，通过可见性驱动统计量量化监督强度，用于场景划分和梯度补偿，解决大规模航空场景重建中内存消耗大和视点覆盖不均的问题，在多种数据集上优于现有方法。
中文摘要 AI 辅助
大规模场景重建是机器人自主系统（如三维地图构建和自动驾驶）中的一项关键基础技术。近年来，3D高斯泼溅（3DGS）在视觉质量和计算效率方面均展现出显著优势，使其成为大规模场景重建的一种有前景的表示方法。然而，在大规模场景中，它仍面临诸多挑战，包括由无人机采集导致的过度内存消耗和不均匀的视点覆盖，这限制了其实际应用。为解决这些问题，我们提出了VDGS，一种新颖的3DGS框架，该框架将相机分布纳入场景建模。VDGS引入了针对场景锚点的可见性驱动统计量，以量化监督强度。这些统计量进一步用于场景划分以及欠优化区域的梯度补偿，从而促进不同区域间的平衡优化。在多个大规模航空场景数据集上进行的大量实验表明，在视点分布不平衡的情况下，VDGS持续优于现有方法，同时在视点分布更均匀的场景中保持具有竞争力的性能。
英文摘要
Large-scale scene reconstruction is a critical foundational technology in robotic autonomous systems such as 3D mapping and autonomous driving. In recent years, 3D Gaussian Splatting (3DGS) has demonstrated remarkable advantages in both visual quality and computational efficiency, making it a promising representation for large-scale scene reconstruction. However, it still faces challenges in large-scale scenes, including excessive memory consumption and uneven viewpoint coverage caused by UAV acquisition, limiting its real-world applications. To address this, we propose VDGS, a novel 3DGS framework that incorporates camera distribution into scene modeling. VDGS introduces visibility-driven statistics for scene anchors to quantify supervision strength. These statistics are further leveraged for scene partitioning and for gradient compensation in under-optimized regions, thereby promoting balanced optimization across different regions. Extensive experiments on multiple large-scale aerial scene datasets demonstrate that, under imbalanced viewpoint distributions, VDGS consistently outperforms existing methods, while maintaining competitive performance in scenarios with more uniform view distributions.
发表机构
- Beijing Institute of Technology（北京理工大学）
- Guangzhou Saite Intelligent Technology Co., Ltd.（广州赛特智能科技有限公司）
机构由 AI 辅助整理，请以论文原文为准。
