Premium
Template Assembly for Detailed Urban Reconstruction
Author(s) -
Nan Liangliang,
Jiang Caigui,
Ghanem Bernard,
Wonka Peter
Publication year - 2015
Publication title -
computer graphics forum
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.578
H-Index - 120
eISSN - 1467-8659
pISSN - 0167-7055
DOI - 10.1111/cgf.12554
Subject(s) - template , computer science , point cloud , texture synthesis , preprocessor , consistency (knowledge bases) , artificial intelligence , set (abstract data type) , computer vision , computer graphics (images) , structure from motion , template matching , matching (statistics) , point (geometry) , image (mathematics) , image texture , motion (physics) , image processing , geometry , mathematics , statistics , programming language
We propose a new framework to reconstruct building details by automatically assembling 3D templates on coarse textured building models. In a preprocessing step, we generate an initial coarse model to approximate a point cloud computed using Structure from Motion and Multi View Stereo, and we model a set of 3D templates of facade details. Next, we optimize the initial coarse model to enforce consistency between geometry and appearance (texture images). Then, building details are reconstructed by assembling templates on the textured faces of the coarse model. The 3D templates are automatically chosen and located by our optimization‐based template assembly algorithm that balances image matching and structural regularity. In the results, we demonstrate how our framework can enrich the details of coarse models using various data sets.