Multi-Volume High Resolution RGB-D Mapping with Dynamic Volume Placement

TL;DR

This paper introduces a dynamic multi-volume RGB-D mapping system that enables high-resolution 3D mapping over large, unbounded environments by adaptively managing multiple mapping volumes between CPU and GPU.

Contribution

The novel system dynamically assigns and manages multiple mapping volumes for high-resolution 3D mapping in unbounded spaces, improving resolution and scalability over existing methods.

Findings

Supports spatially extended high-resolution mapping

Efficiently exchanges mapping volumes between CPU and GPU

Adapts volume placement dynamically based on environment

Abstract

We present a novel RGB-D mapping system for generating 3D maps over spatially extended regions with higher resolution than current methods using multiple, dynamically placed mapping volumes. Our method takes in RGB-D frames and dynamically assigns multiple mapping volumes to the environment, exchanging mapping volumes between the CPU and GPU. Mapping volumes are added or removed as needed to allow for spatially extended, high resolution mapping. Our system is designed to maximize the resolution possible for such volumetric methods, while working on an unbounded space.