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.

3D Gaussian human reconstruction algorithm based on depth regularization

Ding Shihao
He Hong
School of Health Science & Engineering, University of Shanghai for Science & Technology, Shanghai 200093, China

Abstract

Due to the lack of additional geometric constraints and prior knowledge, the reconstruction results of existing multi-view 3D human body reconstruction methods are poor in terms of quality and completeness. In response to the above problems, this paper proposed a 3D gaussian reconstruction algorithm DHGS for sparse views. Firstly, improved estimation method for human body model parameters by combining multi-view joint reprojection and intersection-over-union error, utilized accurate body priors to initialize 3D gaussian model. Secondly, proposed an adaptive depth adjustment module that incorporated depth estimation model, achieved depth regularization through differentiable rasterization rendering, and enhanced the geometric consistency of the reconstruction by leveraging human body and depth prior knowledge. Finally, generated synthetic pseudo-views during the optimization process to enforce additional geometric constraints. Experimental results on the ZJU-MoCap, GeneBody, and DNA-Rendering datasets showed that the DHGS algorithm achieved PSNR of 26.13 dB, 24.87 dB, and 25.25 dB for image reconstruction, represented improvements of 27.3%, 32.6%, and 17.4% over the original 3DGS algorithm. The experiments validate the effectiveness of the algorithm, with the DHGS model being capable of training in just 5 minutes to render high-quality 3D human body images in real time.

Foundation Support

国家科技部资助项目(G2021013008)
上海市科学技术委员会资助项目(18070503000)
上海理工大学医工交叉重点资助项目(1020308405,1022308502)

Publish Information

DOI: 10.19734/j.issn.1001-3695.2024.09.0368
Publish at: Application Research of Computers Accepted Paper, Vol. 42, 2025 No. 6

Publish History

[2025-03-06] Accepted Paper

Cite This Article

丁世豪, 何宏. 基于深度正则化的三维高斯人体重建算法 [J]. 计算机应用研究, 2025, 42 (6). (2025-03-10). https://doi.org/10.19734/j.issn.1001-3695.2024.09.0368. (Ding Shihao, He Hong. 3D Gaussian human reconstruction algorithm based on depth regularization [J]. Application Research of Computers, 2025, 42 (6). (2025-03-10). https://doi.org/10.19734/j.issn.1001-3695.2024.09.0368. )

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)