Monocular Online Reconstruction with Enhanced Detail Preservation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wu, Songyin, Lv, Zhaoyang, Zhu, Yufeng, Frost, Duncan, Li, Zhengqin, Yan, Ling-Qi, Ren, Carl, Newcombe, Richard, Dong, Zhao
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915287020863488
author Wu, Songyin
Lv, Zhaoyang
Zhu, Yufeng
Frost, Duncan
Li, Zhengqin
Yan, Ling-Qi
Ren, Carl
Newcombe, Richard
Dong, Zhao
author_facet Wu, Songyin
Lv, Zhaoyang
Zhu, Yufeng
Frost, Duncan
Li, Zhengqin
Yan, Ling-Qi
Ren, Carl
Newcombe, Richard
Dong, Zhao
contents We propose an online 3D Gaussian-based dense mapping framework for photorealistic details reconstruction from a monocular image stream. Our approach addresses two key challenges in monocular online reconstruction: distributing Gaussians without relying on depth maps and ensuring both local and global consistency in the reconstructed maps. To achieve this, we introduce two key modules: the Hierarchical Gaussian Management Module for effective Gaussian distribution and the Global Consistency Optimization Module for maintaining alignment and coherence at all scales. In addition, we present the Multi-level Occupancy Hash Voxels (MOHV), a structure that regularizes Gaussians for capturing details across multiple levels of granularity. MOHV ensures accurate reconstruction of both fine and coarse geometries and textures, preserving intricate details while maintaining overall structural integrity. Compared to state-of-the-art RGB-only and even RGB-D methods, our framework achieves superior reconstruction quality with high computational efficiency. Moreover, it integrates seamlessly with various tracking systems, ensuring generality and scalability.
format Preprint
id arxiv_https___arxiv_org_abs_2505_07887
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Monocular Online Reconstruction with Enhanced Detail Preservation
Wu, Songyin
Lv, Zhaoyang
Zhu, Yufeng
Frost, Duncan
Li, Zhengqin
Yan, Ling-Qi
Ren, Carl
Newcombe, Richard
Dong, Zhao
Graphics
Computer Vision and Pattern Recognition
We propose an online 3D Gaussian-based dense mapping framework for photorealistic details reconstruction from a monocular image stream. Our approach addresses two key challenges in monocular online reconstruction: distributing Gaussians without relying on depth maps and ensuring both local and global consistency in the reconstructed maps. To achieve this, we introduce two key modules: the Hierarchical Gaussian Management Module for effective Gaussian distribution and the Global Consistency Optimization Module for maintaining alignment and coherence at all scales. In addition, we present the Multi-level Occupancy Hash Voxels (MOHV), a structure that regularizes Gaussians for capturing details across multiple levels of granularity. MOHV ensures accurate reconstruction of both fine and coarse geometries and textures, preserving intricate details while maintaining overall structural integrity. Compared to state-of-the-art RGB-only and even RGB-D methods, our framework achieves superior reconstruction quality with high computational efficiency. Moreover, it integrates seamlessly with various tracking systems, ensuring generality and scalability.
title Monocular Online Reconstruction with Enhanced Detail Preservation
topic Graphics
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2505.07887