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

Altsplat:3d Gaussian splatting for novel view Synthesis from sparse inputs

Wei Dong
Du Yunjing
Chen Zhicheng
Li Xuefei
Ren Shuo
School of Information Science and Engineering, Shenyang University of Technology, Shenyang 110870, China
DOI: 10.19734/j.issn.1001-3695.2026.04.0126

Abstract

To address the problems of missing initial point clouds, insufficient densification and simplex loss function in 3D Gaussian Splatting-based novel view synthesis under sparse input conditions, the study develops AltSplat, a novel sparse-input-oriented 3D Gaussian Splatting method, to improve the geometric completeness and rendering quality of synthesized novel views. The method fuses fine-grained point clouds generated by EAP-GS, an attention-based point cloud enhancement module, with dense point clouds reconstructed by COLMAP. This fusion expands the initial point cloud scale and strengthens scene structural consistency. The study designs a frequency-guided densification strategy that operates mutually exclusively with standard densification during the optimization phase. The strategy guides Gaussians to preferentially distribute in edge and detail regions based on image high-frequency structural information, and reduces the growth of invalid and redundant Gaussians. Meanwhile, the study introduces a Gaussian color loss based on low-order spherical harmonic components. This loss constrains Gaussian color representation and mitigates color deviation and rendering artifacts under sparse input conditions. The study conducted comparative experiments under multiple sparse-view settings on the LLFF and Mip-NeRF360 datasets. Results show that the proposed method achieves steady improvements in peak signal-to-noise ratio (PSNR) , structural similarity (SSIM) and learned perceptual image patch similarity (LPIPS) , and produces higher-fidelity synthesized images. The code are publicly available at: https: //github. com/duyunjing888-bit/3DGSforNVSfromSparseInputs

Foundation Support

国家教育部基金2022年度"春晖计划"合作科研项目(20220407)

Publish Information

DOI: 10.19734/j.issn.1001-3695.2026.04.0126
Publish at: Application Research of Computers Accepted Paper, Vol. 44, 2027 No. 1

Publish History

[2026-08-27] Accepted Paper

Cite This Article

魏东, 杜云景, 陈志成, 等. AltSplat:面向稀疏输入的三维高斯溅射新视图合成方法 [J]. 计算机应用研究, 2027, 44 (1). (2026-09-14). https://doi.org/10.19734/j.issn.1001-3695.2026.04.0126. (Wei Dong, Du Yunjing, Chen Zhicheng, et al. Altsplat:3d Gaussian splatting for novel view Synthesis from sparse inputs [J]. Application Research of Computers, 2027, 44 (1). (2026-09-14). https://doi.org/10.19734/j.issn.1001-3695.2026.04.0126. )

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)