HRBF-Fusion: Accurate 3D Reconstruction from RGB-D Data Using On-the-fly Implicits

Author:

Xu Yabin1ORCID,Nan Liangliang2ORCID,Zhou Laishui3,Wang Jun3,Wang Charlie C. L.4ORCID

Affiliation:

1. Nanjing University of Aeronautics and Astronautics, Nanjing, China / Delft University of Technology, The Netherlands

2. Delft University of Technology, The Netherlands

3. Nanjing University of Aeronautics and Astronautics, China

4. The University of Manchester, United Kingdom / Delft University of Technology, The Netherlands

Abstract

Reconstruction of high-fidelity 3D objects or scenes is a fundamental research problem. Recent advances in RGB-D fusion have demonstrated the potential of producing 3D models from consumer-level RGB-D cameras. However, due to the discrete nature and limited resolution of their surface representations (e.g., point or voxel based), existing approaches suffer from the accumulation of errors in camera tracking and distortion in the reconstruction, which leads to an unsatisfactory 3D reconstruction. In this article, we present a method using on-the-fly implicits of Hermite Radial Basis Functions (HRBFs) as a continuous surface representation for camera tracking in an existing RGB-D fusion framework. Furthermore, curvature estimation and confidence evaluation are coherently derived from the inherent surface properties of the on-the-fly HRBF implicits, which are devoted to a data fusion with better quality. We argue that our continuous but on-the-fly surface representation can effectively mitigate the impact of noise with its robustness and constrain the reconstruction with inherent surface smoothness when being compared with discrete representations. Experimental results on various real-world and synthetic datasets demonstrate that our HRBF-fusion outperforms the state-of-the-art approaches in terms of tracking robustness and reconstruction accuracy.

Funder

National Key Research and Development Program of China

National Natural Science Foundation of China

Natural Science Foundation of Jiangsu Province

Publisher

Association for Computing Machinery (ACM)

Subject

Computer Graphics and Computer-Aided Design

Reference71 articles.

Cited by 13 articles. 订阅此论文施引文献 订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献

1. X-SLAM: Scalable Dense SLAM for Task-aware Optimization using CSFD;ACM Transactions on Graphics;2024-07-19

2. RTG-SLAM: Real-time 3D Reconstruction at Scale using Gaussian Splatting;Special Interest Group on Computer Graphics and Interactive Techniques Conference Conference Papers '24;2024-07-13

3. CIS2VR: CNN-based Indoor Scan to VR Environment Authoring Framework;2024 IEEE International Conference on Artificial Intelligence and eXtended and Virtual Reality (AIxVR);2024-01-17

4. A Survey of Indoor 3D Reconstruction Based on RGB-D Cameras;IEEE Access;2024

5. MIPS-Fusion: Multi-Implicit-Submaps for Scalable and Robust Online Neural RGB-D Reconstruction;ACM Transactions on Graphics;2023-12-05

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3