Open Access3D Indoor Scene Completion via Room Layout Estimation
Author(s) -
Wei Xia,
Rongfeng Lu,
Yaoqi Sun,
Chenghao Xu,
Kun Lv,
Yanwei Jia,
Zunjie Zhu,
Bolun Zheng
Publication year - 2021
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/2025/1/012102
Subject(s) - leverage (statistics) , computer science , computer vision , artificial intelligence , task (project management) , principal (computer security) , computer graphics (images) , operating system , management , economics
Recent advances in 3D reconstructions have shown impressive progress in 3D indoor scene reconstruction, enabling automatic scene modeling; however, holes in the 3D scans hinder the further usage of the reconstructed models. Thus, we propose the task of layout-based hole filling for the incomplete indoor scene scans: from the mesh of a scene model, we estimate the scene layout by detecting the principal planes of a scene and leverage the layout as the prior for the accurate completion of planar regions. Experiments show that guiding scene model completion through the scene layout prior significantly outperforms the alternative approach to the task of scene model completion.