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
App. Res. of Comp. Accepted Paper
Vol. 42, 2025 No. 9

Cross-view consistency based 3D Gaussian splatting interactive segmentation method

Xu Zhixianga
Lyu Zejuna
Zhang Yancia,b
a. College of Computer Science, b. National Key Fundamental Science on Synthetic Vision, Sichuan University, Chengdu 610065, China
DOI: 10.19734/j.issn.1001-3695.2024.12.0525

Abstract

Existing 3D Gaussian Splatting interactive segmentation methods suffer from long processing times and difficulties in achieving clear object boundary segmentation, failing to meet the demands of single-object editing in digital asset generation and related fields. To address this, this paper proposes a cross-view consistency based 3D Gaussian Splatting interactive segmentation method. The core idea involves achieving cross-view consistency segmentation in 2D images followed by local reconstruction of target object through 3D Gaussian Splatting. Specifically, this method iteratively performs cross-view consistency segmentation using a self-prompting strategy on visual hull, while introducing a clip rejection mechanism to handle segmentation failures during iterations. Additionally, region restriction and post-processing strategies are proposed to address occlusion scenarios. Experimental results demonstrate that this method not only achieves precise object boundary segmentation but also a 2 to 6 times speed improvement. This proves that the method's advantages in both quality and efficiency for tasks like scene editing.

Foundation Support

四川省重点研发项目(2023YFG0122)

Publish Information

DOI: 10.19734/j.issn.1001-3695.2024.12.0525
Publish at: Application Research of Computers Accepted Paper, Vol. 42, 2025 No. 9

Publish History

[2025-04-29] Accepted Paper

Cite This Article

徐知祥, 吕泽均, 张严辞. 基于跨视角一致性的3D高斯溅射交互式分割方法 [J]. 计算机应用研究, 2025, 42 (9). (2025-04-29). https://doi.org/10.19734/j.issn.1001-3695.2024.12.0525. (Xu Zhixiang, Lyu Zejun, Zhang Yanci. Cross-view consistency based 3D Gaussian splatting interactive segmentation method [J]. Application Research of Computers, 2025, 42 (9). (2025-04-29). https://doi.org/10.19734/j.issn.1001-3695.2024.12.0525. )

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)