EC-SLAM: Real-time Dense Neural RGB-D SLAM System with Effectively Constrained Global Bundle Adjustment
CoRR(2024)
摘要
We introduce EC-SLAM, a real-time dense RGB-D simultaneous localization and
mapping (SLAM) system utilizing Neural Radiance Fields (NeRF). Although recent
NeRF-based SLAM systems have demonstrated encouraging outcomes, they have yet
to completely leverage NeRF's capability to constrain pose optimization. By
employing an effectively constrained global bundle adjustment (BA) strategy,
our system makes use of NeRF's implicit loop closure correction capability.
This improves the tracking accuracy by reinforcing the constraints on the
keyframes that are most pertinent to the optimized current frame. In addition,
by implementing a feature-based and uniform sampling strategy that minimizes
the number of ineffective constraint points for pose optimization, we mitigate
the effects of random sampling in NeRF. EC-SLAM utilizes sparse parametric
encodings and the truncated signed distance field (TSDF) to represent the map
in order to facilitate efficient fusion, resulting in reduced model parameters
and accelerated convergence velocity. A comprehensive evaluation conducted on
the Replica, ScanNet, and TUM datasets showcases cutting-edge performance,
including enhanced reconstruction accuracy resulting from precise pose
estimation, 21 Hz run time, and tracking precision improvements of up to 50%.
The source code is available at https://github.com/Lightingooo/EC-SLAM.
更多查看译文
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要