EC-SLAM: Effectively Constrained Neural RGB-D SLAM with Sparse TSDF Encoding and Global Bundle Adjustment

TL;DR

EC-SLAM is a real-time dense RGB-D SLAM system that leverages neural radiance fields with sparse encoding and global bundle adjustment to improve accuracy and efficiency in pose estimation and mapping.

Contribution

The paper introduces a novel SLAM system combining sparse TSDF encoding with NeRF and a globally constrained bundle adjustment for enhanced accuracy and real-time performance.

Findings

Achieves state-of-the-art accuracy on multiple datasets.

Operates in real-time at up to 21 Hz.

Improves pose optimization through global constraints and efficient sampling.

Abstract

We introduce EC-SLAM, a real-time dense RGB-D simultaneous localization and mapping (SLAM) system leveraging Neural Radiance Fields (NeRF). While recent NeRF-based SLAM systems have shown promising results, they have yet to fully exploit NeRF's potential to constrain pose optimization. EC-SLAM addresses this by using sparse parametric encodings and Truncated Signed Distance Fields (TSDF) to represent the map, enabling efficient fusion, reducing model parameters, and accelerating convergence. Our system also employs a globally constrained Bundle Adjustment (BA) strategy that capitalizes on NeRF's implicit loop closure correction capability, improving tracking accuracy by reinforcing constraints on keyframes most relevant to the current optimized frame. Furthermore, by integrating a feature-based and uniform sampling strategy that minimizes ineffective constraint points for pose optimization, we reduce the impact of random sampling in NeRF. Extensive evaluations on the Replica, ScanNet, and TUM datasets demonstrate state-of-the-art performance, with precise tracking and reconstruction accuracy achieved alongside real-time operation at up to 21 Hz.