Vox-Fusion++: Voxel-based Neural Implicit Dense Tracking and Mapping with Multi-maps

TL;DR

Vox-Fusion++ is a real-time, multi-maps dense mapping system that combines neural implicit surfaces with traditional volumetric methods, improving accuracy and scalability for large-scale scene reconstruction in AR and collaborative mapping.

Contribution

It introduces a voxel-based neural implicit surface representation with multi-maps, octree-based scene division, and a multi-process framework for real-time dense mapping.

Findings

Outperforms previous methods in reconstruction quality and accuracy.

Effective handling of large-scale scenes with multi-maps.

Suitable for real-time AR and collaborative mapping applications.

Abstract

In this paper, we introduce Vox-Fusion++, a multi-maps-based robust dense tracking and mapping system that seamlessly fuses neural implicit representations with traditional volumetric fusion techniques. Building upon the concept of implicit mapping and positioning systems, our approach extends its applicability to real-world scenarios. Our system employs a voxel-based neural implicit surface representation, enabling efficient encoding and optimization of the scene within each voxel. To handle diverse environments without prior knowledge, we incorporate an octree-based structure for scene division and dynamic expansion. To achieve real-time performance, we propose a high-performance multi-process framework. This ensures the system's suitability for applications with stringent time constraints. Additionally, we adopt the idea of multi-maps to handle large-scale scenes, and leverage loop detection and hierarchical pose optimization strategies to reduce long-term pose drift and remove duplicate geometry. Through comprehensive evaluations, we demonstrate that our method outperforms previous methods in terms of reconstruction quality and accuracy across various scenarios. We also show that our Vox-Fusion++ can be used in augmented reality and collaborative mapping applications. Our source code will be publicly available at \url{https://github.com/zju3dv/Vox-Fusion_Plus_Plus}