中国科学院自动化研究所机构知识库

Facade labeling, namely semantically segmenting the facade images, requires exploiting the facade regularity. To model the regular-ity, this paper proposes a novel matrix multiplication based formulation. In the model, the regularity is described as generalized translation sym-metry (GTS) which enables varying distances between the repeated elements. Moreover, an explicit and intuitive formulation via matrix multi-plication is also derived for the GTS. That is, the symmetry is interpreted as the product of a repetitive pattern and two block matrices. These two block matrices respectively represent the vertical and horizontal repe-titions. Based on the formulation, facade labeling is reformulated into factorizing the facade to calculate the block matrices. An alternating op-timization algorithm is thus developed to solve the matrix factorization problem, where dynamic programming is used to optimize the block ma-trices. Extensive experiments demonstrate the fidelity of our model and the efficiency of the algorithm.