Multi-Volume High Resolution RGB-D Mapping with Dynamic Volume Placement
This addresses the challenge of scalable, high-resolution RGB-D mapping for robotics or AR/VR applications, though it appears incremental as it builds on existing volumetric methods.
The paper tackles the problem of generating high-resolution 3D maps over large areas by introducing a system that uses multiple, dynamically placed mapping volumes to manage computational resources between CPU and GPU, achieving higher resolution than current methods in unbounded spaces.
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.