NeRF and Gaussian Splatting SLAM in the Wild
This work addresses the gap in understanding SLAM performance in unstructured outdoor settings, providing a benchmark for researchers in robotics and computer vision, though it is incremental as it evaluates existing methods on new data.
This study evaluated neural radiance fields (NeRF) and Gaussian Splatting-based SLAM methods against traditional approaches in outdoor environments, finding that neural methods offer superior robustness in challenging conditions like low light but with high computational cost, while traditional methods perform best across seasons but are sensitive to lighting variations.
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.