An Efficient Volumetric Mesh Representation for Real-time Scene Reconstruction using Spatial Hashing

TL;DR

This paper introduces a novel, efficient volumetric mesh framework using spatial hashing for real-time scene reconstruction, significantly reducing memory use and maintaining high speed in online applications.

Contribution

The paper presents a new volumetric mesh representation with spatial hashing and Hamming distance refinement, optimized for online scene reconstruction and parallel GPU processing.

Findings

Reduces mesh memory consumption significantly.

Maintains high reconstruction speed in real-time.

Improves mesh quality with low computational cost.

Abstract

Mesh plays an indispensable role in dense real-time reconstruction essential in robotics. Efforts have been made to maintain flexible data structures for 3D data fusion, yet an efficient incremental framework specifically designed for online mesh storage and manipulation is missing. We propose a novel framework to compactly generate, update, and refine mesh for scene reconstruction upon a volumetric representation. Maintaining a spatial-hashed field of cubes, we distribute vertices with continuous value on discrete edges that support O(1) vertex accessing and forbid memory redundancy. By introducing Hamming distance in mesh refinement, we further improve the mesh quality regarding the triangle type consistency with a low cost. Lock-based and lock-free operations were applied to avoid thread conflicts in GPU parallel computation. Experiments demonstrate that the mesh memory consumption is significantly reduced while the running speed is kept in the online reconstruction process.