In accordance with regulations and requirements, the editorial department's website domain has been changed to arocmag.cn. The original domain (arocmag.com) has been redirecting to new domain since Jan. 1st, 2025.
See More
Technology of Graphic & Image
|
App. Res. of Comp. Printed Article
Vol. 42, 2025 No. 5
1570-1575

Fast neural implicit surface reconstruction algorithm with monocular priors

Wu Jinhua,b,c
Yang Xiaojuna,b,c
Wang Jingb,c,d
a. School of Information Engineering, b. Key Laboratory of Photonic Technology for Integrated Sensing & Communication, Ministry of Education of China, c. Guangdong Provincial Key Laboratory of Information Photonics Technology, d. School of Integrated Circuit, Guangdong University of Technology, Guangzhou 510006, China
DOI: 10.19734/j.issn.1001-3695.2024.07.0270

Abstract

In recent years, neural implicit surface reconstruction methods have become a popular technique for multi-view 3D reconstruction. However, existing methods suffer from several drawbacks, primarily long training times for two main reasons. Firstly, there are numerous empty regions between the camera and the object surface, where the information contributes little to the final reconstruction quality. Secondly, each ray sample queries large multilayer perceptrons(MLPs), which introduces heavy computational burdens during training and affects efficiency. Additionally, the lack of geometric constraints during 3D reconstruction results in suboptimal reconstruction outcomes. To address these issues, this paper proposed the FM-NeuS algorithm. It reduced the number of sampling points per ray by skipping empty regions and terminating rays at occluded areas during ray traversal, thus accelerating model training. It adopted a lightweight MLP with multi-resolution hash encoding to speed up the query efficiency of sampling points, reduce training time, and enhanced the surface details of reconstructed objects. It used monocular priors to constrain surface geometry and improve reconstruction quality. Extensive experiments demonstrate that this proposed method can produce high-quality surfaces and achieve training speeds 20 times faster than NeuS.

Foundation Support

国家自然科学基金资助项目(62373112)
广州市科技攻关资助项目(202206010104)

Publish Information

DOI: 10.19734/j.issn.1001-3695.2024.07.0270
Publish at: Application Research of Computers Printed Article, Vol. 42, 2025 No. 5
Section: Technology of Graphic & Image
Pages: 1570-1575
Serial Number: 1001-3695(2025)05-038-1570-06

Publish History

[2025-05-05] Printed Article

Cite This Article

吴锦湖, 杨晓君, 王靖. 融合单目先验信息的快速神经隐式表面重建算法 [J]. 计算机应用研究, 2025, 42 (5): 1570-1575. (Wu Jinhu, Yang Xiaojun, Wang Jing. Fast neural implicit surface reconstruction algorithm with monocular priors [J]. Application Research of Computers, 2025, 42 (5): 1570-1575. )

About the Journal

  • Application Research of Computers Monthly Journal
  • Journal ID ISSN 1001-3695
    CN  51-1196/TP

Application Research of Computers, founded in 1984, is an academic journal of computing technology sponsored by Sichuan Institute of Computer Sciences under the Science and Technology Department of Sichuan Province.

Aiming at the urgently needed cutting-edge technology in this discipline, Application Research of Computers reflects the mainstream technology, hot technology and the latest development trend of computer application research at home and abroad in a timely manner. The main contents of the journal include high-level academic papers in this discipline, the latest scientific research results and major application results. The contents of the columns involve new theories of computer discipline, basic computer theory, algorithm theory research, algorithm design and analysis, blockchain technology, system software and software engineering technology, pattern recognition and artificial intelligence, architecture, advanced computing, parallel processing, database technology, computer network and communication technology, information security technology, computer image graphics and its latest hot application technology.

Application Research of Computers has many high-level readers and authors, and its readers are mainly senior and middle-level researchers and engineers engaged in the field of computer science, as well as teachers and students majoring in computer science and related majors in colleges and universities. Over the years, the total citation frequency and Web download rate of Application Research of Computers have been ranked among the top of similar academic journals in this discipline, and the academic papers published are highly popular among the readers for their novelty, academics, foresight, orientation and practicality.

Indexed & Evaluation

  • The Second National Periodical Award 100 Key Journals
  • Double Effect Journal of China Journal Formation
  • the Core Journal of China (Peking University 2023 Edition)
  • the Core Journal for Science
  • Chinese Science Citation Database (CSCD) Source Journals
  • RCCSE Chinese Core Academic Journals
  • Journal of China Computer Federation
  • 2020-2022 The World Journal Clout Index (WJCI) Report of Scientific and Technological Periodicals
  • Full-text Source Journal of China Science and Technology Periodicals Database
  • Source Journal of China Academic Journals Comprehensive Evaluation Database
  • Source Journals of China Academic Journals (CD-ROM Version), China Journal Network
  • 2017-2019 China Outstanding Academic Journals with International Influence (Natural Science and Engineering Technology)
  • Source Journal of Top Academic Papers (F5000) Program of China's Excellent Science and Technology Journals
  • Source Journal of China Engineering Technology Electronic Information Network and Electronic Technology Literature Database
  • Source Journal of British Science Digest (INSPEC)
  • Japan Science and Technology Agency (JST) Source Journal
  • Russian Journal of Abstracts (AJ, VINITI) Source Journals
  • Full-text Journal of EBSCO, USA
  • Cambridge Scientific Abstracts (Natural Sciences) (CSA(NS)) core journals
  • Poland Copernicus Index (IC)
  • Ulrichsweb (USA)