Integrating Geometric Priors and Importance Sampling for High-fidelity Indoor Scene Reconstruction

Authors

• Tao Yang, School of Control and Computer Engineering, North China Electric Power University, Beijing 102206, China
• Min Shi, School of Control and Computer Engineering, North China Electric Power University, Beijing 102206, China
• Xigang Zhao, School of Control and Computer Engineering, North China Electric Power University, Beijing 102206, China
• Suqin Wang, School of Control and Computer Engineering, North China Electric Power University, Beijing 102206, China
• Qi Wang, School of Control and Computer Engineering, North China Electric Power University, Beijing 102206, China
• Dengming Zhu, Institute of Computing Technology, Chinese Academy of Sciences, Beijing 100190, China; Taicang-CAS Institute of Information and Technology, Taicang 215400, China

Abstract

Abstract: Gaussian splatting suffers from geometric distortion during scene reconstruction, particularly in weakly textured indoor scenes. To address this issue, this paper proposes a high-precision indoor scene reconstruction method that integrates geometric priors and importance sampling. The proposed method fully considers the effect of the initialization process on reconstruction quality. An advanced feed-forward model is employed to generate high-quality geometric initialization, thus improving overall reconstruction stability and accuracy. An importance sampling strategy is introduced to mitigate the adverse effects of blurry images. Furthermore, a supervision mechanism based on a geometric prior model is designed to constrain the scene structure, further enhancing geometric consistency and reconstruction accuracy. Experimental results show that the proposed method improves reconstruction quality and effectively alleviates geometric structural distortion in indoor scene reconstruction.

Recommended Citation

Yang, Tao; Shi, Min; Zhao, Xigang; Wang, Suqin; Wang, Qi; and Zhu, Dengming (2026) "Integrating Geometric Priors and Importance Sampling for High-fidelity Indoor Scene Reconstruction," Journal of System Simulation: Vol. 38: Iss. 3, Article 4.
DOI: 10.16182/j.issn1004731x.joss.25-1055
Available at: https://dc-china-simulation.researchcommons.org/journal/vol38/iss3/4

First Page

584

Last Page

594

CLC

TP37

Recommended Citation

Yang Tao, Shi Min, Zhao Xigang, et al. Integrating Geometric Priors and Importance Sampling for High-fidelity Indoor Scene Reconstruction[J]. Journal of System Simulation, 2026, 38(3): 584-594.

Corresponding Author

Shi Min

DOI

10.16182/j.issn1004731x.joss.25-1055