NIS-SLAM: Neural Implicit Semantic RGB-D SLAM for 3D Consistent Scene Understanding

TL;DR

NIS-SLAM introduces a neural implicit RGB-D SLAM system that integrates semantic segmentation and multi-resolution features for accurate 3D scene understanding and reconstruction, demonstrating superior performance and AR applications.

Contribution

The paper presents a novel neural implicit SLAM framework combining semantic segmentation, multi-resolution features, and a fusion strategy for consistent scene understanding.

Findings

Outperforms existing neural implicit SLAM methods in accuracy

Achieves high-fidelity surface reconstruction and semantic consistency

Demonstrates effectiveness in augmented reality applications

Abstract

In recent years, the paradigm of neural implicit representations has gained substantial attention in the field of Simultaneous Localization and Mapping (SLAM). However, a notable gap exists in the existing approaches when it comes to scene understanding. In this paper, we introduce NIS-SLAM, an efficient neural implicit semantic RGB-D SLAM system, that leverages a pre-trained 2D segmentation network to learn consistent semantic representations. Specifically, for high-fidelity surface reconstruction and spatial consistent scene understanding, we combine high-frequency multi-resolution tetrahedron-based features and low-frequency positional encoding as the implicit scene representations. Besides, to address the inconsistency of 2D segmentation results from multiple views, we propose a fusion strategy that integrates the semantic probabilities from previous non-keyframes into keyframes to achieve consistent semantic learning. Furthermore, we implement a confidence-based pixel sampling and progressive optimization weight function for robust camera tracking. Extensive experimental results on various datasets show the better or more competitive performance of our system when compared to other existing neural dense implicit RGB-D SLAM approaches. Finally, we also show that our approach can be used in augmented reality applications. Project page: \href{https://zju3dv.github.io/nis_slam}{https://zju3dv.github.io/nis\_slam}.