App. Res. of Comp. Accepted Paper
Vol. 44, 2027 No. 1

Redundancy-aware progressive structural compression method for 3D Gaussian splatting

Sun Fanshu1a,1b,2
Kuang Liqun1a,1b,2
Qin Yanting1a,1b,2
Chen Zhongyu1a,1b,2
Jiao Shichao1a,1b,2
Xiong Fengguang1a,1b,2
1. North University of China a. School of Computer Science and Technology, b. Shanxi Key Laboratory of Machine Vision & Virtual Reality, Taiyuan 030051, China
2. Shanxi Vision Information Processing and Intelligent Robot Engineering Research Center, Taiyuan 030051, China
DOI: 10.19734/j.issn.1001-3695.2026.04.0128

Abstract

3D Gaussian Splatting has attracted widespread attention due to its favorable balance between rendering efficiency and image quality. However, its adaptive densification mechanism generates numerous redundant Gaussian primitives during training, increasing computational and storage overhead. To address this issue, this paper proposed a Redundancy-aware Progressive Structural Compression for Gaussian Splatting (RPSC-GS) method. It introduced an optimizable validity variable during training to continuously model the long-term rendering contribution of each Gaussian primitive and guided the variable to converge to a discrete state. Based on the validity representation, it designed a progressive structural compression mechanism that combined local redundancy estimation, a minimum redundancy propagation strategy, and transparency statistics to identify and physically remove highly overlapping Gaussian primitives with low visual contributions. It further designed a global transparency supplementary pruning strategy to eliminate weakly visible noise. Experimental results show that, compared with the 3DGS baseline, RPSC-GS improves the average rendering speed by approximately 173%, 229%, and 318% on three standard datasets, respectively, while reducing peak GPU memory consumption by up to 44% in representative scenes. The results demonstrate that the proposed method effectively improves rendering efficiency and model compactness while maintaining rendering quality, providing an efficient structural compression solution for real-time 3D scene rendering.

Foundation Support

国家自然科学基金项目(62272426)
山西省科技重大专项计划"揭榜挂帅"项目(202201150401021)
山西省重点研发计划项目(202402020101001)

Publish Information

DOI: 10.19734/j.issn.1001-3695.2026.04.0128
Publish at: Application Research of Computers Accepted Paper, Vol. 44, 2027 No. 1

Publish History

[2026-09-10] Accepted Paper

Cite This Article

孙凡淑, 况立群, 秦妍婷, 等. 面向3D高斯喷溅的冗余感知渐进式结构压缩方法 [J]. 计算机应用研究, 2027, 44 (1). (2026-09-14). https://doi.org/10.19734/j.issn.1001-3695.2026.04.0128. (Sun Fanshu, Kuang Liqun, Qin Yanting, et al. Redundancy-aware progressive structural compression method for 3D Gaussian splatting [J]. Application Research of Computers, 2027, 44 (1). (2026-09-14). https://doi.org/10.19734/j.issn.1001-3695.2026.04.0128. )

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)