对比神经与传统方法在户外复杂环境中的定位表现。
NeRF and Gaussian Splatting SLAM in the Wild
- 在真实户外场景中测试NeRF与高斯点渲染的SLAM性能
- 神经方法在弱光下更稳定但计算开销大
- 传统方法跨季节表现好但对光照敏感
在动态场景、光照变化和季节性差异的户外环境中，基于视觉的同步定位与地图构建（SLAM）面临严峻挑战，亟需鲁棒性强的解决方案。尽管传统SLAM方法适应性差，基于深度学习的神经辐射场（NeRF）和高斯点渲染（Gaussian Splatting）等新兴方法展现出潜力。然而，这些方法大多仅在受控的室内环境中评估，缺乏对非结构化、多变户外场景的系统分析。本研究填补了这一空白，在自然户外环境下全面评估了这些方法在相机跟踪精度、环境适应性及计算效率方面的表现，揭示出显著的权衡关系。大量实验表明，神经类SLAM方法在低光等恶劣条件下具有更强鲁棒性，但计算成本高昂；而传统方法在跨季节任务中表现最优，却对光照变化极为敏感。相关基准代码已公开于https://github.com/iis-esslingen/nerf-3dgs-benchmark。
原文摘要 · Abstract (English)
Navigating outdoor environments with visual Simultaneous Localization and Mapping (SLAM) systems poses significant challenges due to dynamic scenes, lighting variations, and seasonal changes, requiring robust solutions. While traditional SLAM methods struggle with adaptability, deep learning-based approaches and emerging neural radiance fields as well as Gaussian Splatting-based SLAM methods, offer promising alternatives. However, these methods have primarily been evaluated in controlled indoor environments with stable conditions, leaving a gap in understanding their performance in unstructured and variable outdoor settings. This study addresses this gap by evaluating these methods in natural outdoor environments, focusing on camera tracking accuracy, robustness to environmental factors, and computational efficiency, highlighting distinct trade-offs. Extensive evaluations demonstrate that neural SLAM methods achieve superior robustness, particularly under challenging conditions such as low light, but at a high computational cost. At the same time, traditional methods perform the best across seasons but are highly sensitive to variations in lighting conditions. The code of the benchmark is publicly available at https://github.com/iis-esslingen/nerf-3dgs-benchmark.
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。