S3-SLAM: Sparse Tri-plane Encoding for Neural Implicit SLAM

TL;DR

S3-SLAM introduces a sparse tri-plane encoding method that significantly reduces parameter count while maintaining high-quality scene reconstruction and rapid SLAM performance.

Contribution

The paper proposes a novel sparse tri-plane encoding technique for neural implicit SLAM, enabling efficient high-resolution scene reconstruction with minimal parameters.

Findings

Achieves scene reconstruction at 512 resolution using only 2-4% of tri-plane parameters.

Provides rapid and high-quality SLAM tracking and mapping.

Demonstrates competitive results on multiple datasets.

Abstract

With the emergence of Neural Radiance Fields (NeRF), neural implicit representations have gained widespread applications across various domains, including simultaneous localization and mapping. However, current neural implicit SLAM faces a challenging trade-off problem between performance and the number of parameters. To address this problem, we propose sparse tri-plane encoding, which efficiently achieves scene reconstruction at resolutions up to 512 using only 2~4% of the commonly used tri-plane parameters (reduced from 100MB to 2~4MB). On this basis, we design S3-SLAM to achieve rapid and high-quality tracking and mapping through sparsifying plane parameters and integrating orthogonal features of tri-plane. Furthermore, we develop hierarchical bundle adjustment to achieve globally consistent geometric structures and reconstruct high-resolution appearance. Experimental results demonstrate that our approach achieves competitive tracking and scene reconstruction with minimal parameters on three datasets. Source code will soon be available.