MuSR: Multi-Scale 3D Scenes Reconstruction based on Monocular Video
Han Gao, Hao Wu, Peiwen Dong, Yixin Xu, Fengyuan Xu, Sheng Zhong
Abstract
Three-dimensional (3D) scene reconstruction, particularly from monocular videos, is a significant challenge in large-scale scenarios due to difficulty handling varying object sizes and high computational resource needs. This paper introduces MuSR, a novel multi-scale reconstruction method addressing these issues. MuSR features a dynamic multi-resolution spatial structure that adaptively adjusts voxel resolution for objects of different sizes to improve reconstruction quality. MuSR also employs a block-based sparse 3D data structure and hardware resource management strategy to reduce GPU memory usage while maintaining efficient reconstruction. Evaluated on ScanNet and 7-Scenes datasets, as well as real-world scenes, MuSR outperforms state-of-the-art methods in terms of efficiency, completeness, and geometric shape reconstruction, proving its applicability in practical multi-scale 3D reconstructions.
BibTeX
@inproceedings{icassp2024_musrmultiscale3d,
title = {MuSR: Multi-Scale 3D Scenes Reconstruction based on Monocular Video},
author = {Han Gao and Hao Wu and Peiwen Dong and Yixin Xu and Fengyuan Xu and Sheng Zhong},
booktitle = {ICASSP 2024},
year = {2024}
}