ACM Transactions on Graphics (Proc. of SIGGRAPH Asia), 2014
Figure 1: Starting from a single image (Input) a user can specify a building mass model and mark shapes (windows, doors, ornaments) on the observed part of a building facade in a rectified image (Element Selection). Our structure completion framework can complete the missing part of the layout (Structure Completion). A 2D and a 3D rendering of the completed models is shown on the right.
We present a method to complete missing structures in facade layouts.Starting from an abstraction of the partially observed layout as a set of shapes, we can propose one or multiple possible completed layouts. Structure completion with large missing parts is an ill-posed problem. Therefore, we combine two sources of information to derive our solution: the observed shapes and a database of complete layouts. The problem is also very difficult, because shape positions and attributes have to be estimated jointly. Our proposed solution is to break the problem into two components: a statistical model to evaluate layouts and a planning algorithm to generate candidate layouts. This ensures that the completed result is consistent with the observation and the layouts in the database.
Figure 2: Completion of a series of buildings along a street occluded by trees.
Figure 3: Several 3D models created using completion results.
We would like to thank all the reviewers for their constructive comments. This research was partially funded by the Visual Computing Center of King Abdullah University of Science and Technology (KAUST), the National Natural Science Foundation of China (No. 61222206), the One Hundred Talent Project of the Chinese Academy of Sciences, the U.S. National Science Foundation (CCF 0643822), and the Austrian Science Funds (FWF P24600-N23).