NeSLAM: Neural Implicit Mapping and Self-Supervised Feature Tracking With Depth Completion and Denoising

TL;DR

NeSLAM introduces a neural implicit mapping framework that combines depth completion, denoising, and self-supervised feature tracking with SDF representation to improve 3D reconstruction and camera localization in indoor environments.

Contribution

The paper presents a novel NeSLAM system integrating depth completion, SDF scene representation, and self-supervised tracking for enhanced indoor 3D mapping.

Findings

Achieves accurate dense depth estimation from noisy sparse data.

Provides robust real-time camera tracking in indoor scenes.

Delivers high-quality scene reconstruction and view synthesis.

Abstract

In recent years, there have been significant advancements in 3D reconstruction and dense RGB-D SLAM systems. One notable development is the application of Neural Radiance Fields (NeRF) in these systems, which utilizes implicit neural representation to encode 3D scenes. This extension of NeRF to SLAM has shown promising results. However, the depth images obtained from consumer-grade RGB-D sensors are often sparse and noisy, which poses significant challenges for 3D reconstruction and affects the accuracy of the representation of the scene geometry. Moreover, the original hierarchical feature grid with occupancy value is inaccurate for scene geometry representation. Furthermore, the existing methods select random pixels for camera tracking, which leads to inaccurate localization and is not robust in real-world indoor environments. To this end, we present NeSLAM, an advanced framework that achieves accurate and dense depth estimation, robust camera tracking, and realistic synthesis of novel views. First, a depth completion and denoising network is designed to provide dense geometry prior and guide the neural implicit representation optimization. Second, the occupancy scene representation is replaced with Signed Distance Field (SDF) hierarchical scene representation for high-quality reconstruction and view synthesis. Furthermore, we also propose a NeRF-based self-supervised feature tracking algorithm for robust real-time tracking. Experiments on various indoor datasets demonstrate the effectiveness and accuracy of the system in reconstruction, tracking quality, and novel view synthesis.