Translational Symmetry-Aware Facade Parsing for 3-D Building Reconstruction

Abstract

Effectively parsing the facade is essential to 3-D building reconstruction, which is a significant computer vision problem for digital entertainment. Although having achieved the promising results in semantic parsing, deep learning methods cannot directly make use of the architectural rules that play an important role in man-made structures. This article presents a novel translational symmetry-based approach. The unified facade parsing network integrates both segmentation and detection branches as the base parser. A translational symmetry measurement-based module is proposed to refine the initial results. After converting the facades into shape grammars, we employ an off-the-shelf rendering engine like Blender to reconstruct the high-quality 3-D models using procedural modeling. We conduct experiments on three public datasets, where our proposed approach outperforms the state-of-the-art methods.