Exploring the capabilities of Neural Radiance Fields (NeRF) and Gaussian-based methods in the context of 3D scene reconstruction, this study contrasts these modern approaches with traditional Simultaneous Localization and Mapping (SLAM) systems. Utilizing datasets such as Replica and ScanNet, we assess performance based on tracking accuracy, mapping fidelity, and view synthesis. Findings reveal that NeRF excels in view synthesis, offering unique capabilities in generating new perspectives from existing data, albeit at slower processing speeds. Conversely, Gaussian-based methods provide rapid processing and significant expressiveness but lack comprehensive scene completion. Enhanced by global optimization and loop closure techniques, newer methods like NICE-SLAM and SplaTAM not only surpass older frameworks such as ORB-SLAM2 in terms of robustness but also demonstrate superior performance in dynamic and complex environments. This comparative analysis bridges theoretical research with practical implications, shedding light on future developments in robust 3D scene reconstruction across various real-world applications.
@article{arxiv.2408.04268,
title = {Evaluating Modern Approaches in 3D Scene Reconstruction: NeRF vs Gaussian-Based Methods},
author = {Yiming Zhou and Zixuan Zeng and Andi Chen and Xiaofan Zhou and Haowei Ni and Shiyao Zhang and Panfeng Li and Liangxi Liu and Mengyao Zheng and Xupeng Chen},
journal= {arXiv preprint arXiv:2408.04268},
year = {2024}
}
Comments
Accepted by 2024 6th International Conference on Data-driven Optimization of Complex Systems