Co-SLAM: Joint Coordinate and Sparse Parametric Encodings for Neural Real-Time SLAM

By Hengyi Wang, Lourdes de Agapito. Computer Vision and Pattern Recognition, 2023

346 citations recorded by the source corpus.

We present Co-SLAM, a neural RGB-D SLAM system based on a hybrid representation, that performs robust camera tracking and high-fidelity surface reconstruction in real time. Co-SLAM represents the scene as a multi-resolution hash-grid to exploit its high convergence speed and ability to represent high-frequency local features. In addition, Co-SLAM incorporates one-blob encoding, to encourage surface coherence and completion in unobserved areas. This joint parametric-coordinate encoding enables real-time and robust performance by bringing the best of both worlds: fast convergence and surface hole filling. Moreover, our ray sampling strategy allows Co-SLAM to perform global bundle adjustment over all keyframes instead of requiring keyframe selection to maintain a small number of active keyframes as competing neural SLAM approaches do. Experimental results show that Co-SLAM runs at 10-17Hz and achieves state-of-the-art scene reconstruction results, and competitive tracking performance in various datasets and benchmarks (ScanNet, TUM, Replica, Synthetic RGBD). Project page: https://hengyiwang.github.io/projects/CoSLAM

Subfields: Aerospace Engineering, Computer Vision and Pattern Recognition, Geology

View Paper: https://www.semanticscholar.org/paper/11c7ae59e24256d729af1630334dbeeea79b14e1

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Aerospace Engineering

1. Nikhil Varma Keetha
2. Deva Ramanan
3. Jay Karhade
4. Sebastian A. Scherer
5. Jonathon Luiten
6. Gengshan Yang
7. Krishna Murthy Jatavallabhula

In Computer Vision and Pattern Recognition

1. Jonathon Luiten
2. Gengshan Yang
3. Krishna Murthy Jatavallabhula
4. Nikhil Varma Keetha
5. Deva Ramanan
6. Jay Karhade
7. Sebastian A. Scherer
8. Philip H. S. Torr

In Geology

1. Deva Ramanan

Citations in the corpus

• SplaTAM: Splat, Track & Map 3D Gaussians for Dense RGB-D SLAM (2023, background): “Following this, a number of works [11, 18, 19, 22, 29, 31, 41, 51, 55], have recently advanced implicit-based SLAM through a number of ways - by reducing catastrophic forgetting via continual learning(experience replay), capturing semantics, incorporating uncertainty, employing efficient resolution…”
• Continuous 3D Perception Model with Persistent State (2025, neutral): “We evaluate scene-level reconstruction on the 7-scenes [67] and NRGBD [4] datasets using accuracy (Acc), completion (Comp), and normal consistency (NC) metrics, as in prior works [4, 81, 82, 86, 104].”