App. Res. of Comp. Accepted Paper
Vol. 43, 2026 No. 7

3D Gaussian-based method for realistic scene reconstruction in autonomous driving

Cao Chunping
Liu Pingsheng
School of Optical-Electrical & Computer Engineering, University of Shanghai for Science & Technology, Shanghai 200093, China
DOI: 10.19734/j.issn.1001-3695.2025.10.0457

Abstract

3D reconstruction of high-fidelity street scenes and view synthesis techniques are crucial for building autonomous driving simulation systems. Due to the lack of structural priors and inter-temporal modeling mechanisms, existing 3D reconstruction methods for self-driving street scenes are prone to geometric misalignment and motion artifacts when dealing with highly dynamic objects. To address the above problems, this paper proposes a high-fidelity reconstruction method of dynamic street scene based on 3D Gaussian. First, dynamic and static regions were separated using vehicle bounding boxes, and structural priors were introduced by incorporating LiDAR point clouds to improve the initialization accuracy of dynamic Gaussian primitives. Second, a Gaussian deformation network with joint spatio-temporal encoding was constructed to model non-rigid vehicle motion. Finally, a pixel gradient-driven adaptive density control strategy was designed to enhance the detail representation capability in dynamic regions. Experimental results on the KITTI and NuScenes datasets demonstrate that the proposed method significantly improves rendering quality and reconstruction efficiency. The peak signal-to-noise ratios reach 27.92 dB and 28.83 dB, respectively, which are 11.3% and 7.8% higher than those of the baseline 3D Gaussian Splatting method. These results indicate that the proposed approach provides a more efficient and reliable three-dimensional environment modeling solution for autonomous driving simulation systems.

Foundation Support

国家级重点研发计划(2021YFF0600605)

Publish Information

DOI: 10.19734/j.issn.1001-3695.2025.10.0457
Publish at: Application Research of Computers Accepted Paper, Vol. 43, 2026 No. 7

Publish History

[2026-03-23] Accepted Paper

Cite This Article

曹春萍, 刘平生. 基于3D高斯的自动驾驶实景重建方法 [J]. 计算机应用研究, 2026, 43 (7). (2026-03-24). https://doi.org/10.19734/j.issn.1001-3695.2025.10.0457. (Cao Chunping, Liu Pingsheng. 3D Gaussian-based method for realistic scene reconstruction in autonomous driving [J]. Application Research of Computers, 2026, 43 (7). (2026-03-24). https://doi.org/10.19734/j.issn.1001-3695.2025.10.0457. )

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)