Accès libre

3D Reconstruction of Indoor Scenes Based on 3DGS Models

Hanghua Li

Hanghua Li

School of Computer Science and Engineering, Xi’an Technological UniversityXi ‘an, China
Recherchez cet auteur sur
Sciendo|Google Scholar
Li, Hanghua
 et 
Lipeng Si

Lipeng Si

School of Computer Science and Engineering, Xi’an Technological UniversityXi ‘an, China
Recherchez cet auteur sur
Sciendo|Google Scholar
Si, Lipeng
  
30 sept. 2024
3D Reconstruction of Indoor Scenes Based on 3DGS Models's Cover Image
À propos de cet article
Article précédent
Article suivant
Citez
Télécharger la couverture
Publié en ligne: 30 sept. 2024
Pages: 56 - 61
DOI: https://doi.org/10.2478/ijanmc-2024-0027
Mots clés
© 2024 Hanghua Li et al., published by Sciendo
This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Figure 1.

3D Reconstruction Process Map.
3D Reconstruction Process Map.

Figure 2.

The result of adding bilateral filters for indoor scenes.
The result of adding bilateral filters for indoor scenes.

Figure 3.

Optimized 3D Reconstruction Process Map.
Optimized 3D Reconstruction Process Map.

Figure 4.

Performance of peak signal-to-noise ratios of 3DGS and ours models for eight different indoor scenes, respectively.
Performance of peak signal-to-noise ratios of 3DGS and ours models for eight different indoor scenes, respectively.

Figure 5.

Representation of structural similarity between 3DGS and ours model for 8 different indoor scenes, respectively.
Representation of structural similarity between 3DGS and ours model for 8 different indoor scenes, respectively.

Experimental Results

Dataset PSNR SSIM
3DGS 30.41 0.879
ours 31.89 0.897
Langue:
Anglais
Périodicité:
4 fois par an
Sujets de la revue:
Informatique, Informatique, autres
RSS Feed de la revue