Journal of System Simulation
Abstract
Abstract: To enhance the geometry reconstruction quality of the GS algorithm in large-scale scene reconstruction, an optimization method constrained by multi-view geometry reconstruction results was proposed. 2D Gaussian planes were used as geometric primitives to overcome depth anisotropy, and dense depth maps generated by DUSt3R and aligned by sparse point clouds were introduced as constraints. By designing a multi-stage optimization strategy that decouples geometry and rendering, the gradient conflict problem in multi-objective training was solved. Experiments on the MatrixCity dataset indicate that the method surpasses comparison methods in related indicators of geometry reconstruction quality and rendering quality in large-scale scenes. The multi-view reconstruction results demonstrate the effectiveness in improving the geometry reconstruction quality of the GS algorithm.
Recommended Citation
Cui, Haohao; Di, Yanqiang; Liu, Qing; and Meng, Xianguo
(2026)
"Three-dimensional Gaussian Reconstruction of Large-scale Scenes Under Multi-view Geometry Constraints,"
Journal of System Simulation: Vol. 38:
Iss.
8, Article 16.
DOI: 10.16182/j.issn1004731x.joss.25-0925
Available at:
https://dc-china-simulation.researchcommons.org/journal/vol38/iss8/16
First Page
2353
Last Page
2363
CLC
TP391.9
Recommended Citation
Cui Haohao, Di Yanqiang, Liu Qing, et al. Three-dimensional Gaussian Reconstruction of Large-scale Scenes Under Multi-view Geometry Constraints[J]. Journal of System Simulation, 2026, 38(8): 2353-2363.
DOI
10.16182/j.issn1004731x.joss.25-0925
Included in
Artificial Intelligence and Robotics Commons, Computer Engineering Commons, Numerical Analysis and Scientific Computing Commons, Operations Research, Systems Engineering and Industrial Engineering Commons, Systems Science Commons