Ecole Centrale Paris, Grande Voie des Vignes 92290, Chatenay-Malabry, France.
IEEE Trans Pattern Anal Mach Intell. 2013 Jul;35(7):1744-56. doi: 10.1109/TPAMI.2012.252.
In this paper, we use shape grammars (SGs) for facade parsing, which amounts to segmenting 2D building facades into balconies, walls, windows, and doors in an architecturally meaningful manner. The main thrust of our work is the introduction of reinforcement learning (RL) techniques to deal with the computational complexity of the problem. RL provides us with techniques such as Q-learning and state aggregation which we exploit to efficiently solve facade parsing. We initially phrase the 1D parsing problem in terms of a Markov Decision Process, paving the way for the application of RL-based tools. We then develop novel techniques for the 2D shape parsing problem that take into account the specificities of the facade parsing problem. Specifically, we use state aggregation to enforce the symmetry of facade floors and demonstrate how to use RL to exploit bottom-up, image-based guidance during optimization. We provide systematic results on the Paris building dataset and obtain state-of-the-art results in a fraction of the time required by previous methods. We validate our method under diverse imaging conditions and make our software and results available online.
在本文中，我们使用形状语法 (SG) 进行立面解析，即将二维建筑立面以建筑上有意义的方式分割为阳台、墙壁、窗户和门。我们工作的主要重点是引入强化学习 (RL) 技术来解决问题的计算复杂性。RL 为我们提供了 Q-learning 和状态聚合等技术，我们利用这些技术来有效地解决立面解析问题。我们最初将 1D 解析问题表述为马尔可夫决策过程，为应用基于 RL 的工具铺平了道路。然后，我们为 2D 形状解析问题开发了新颖的技术，这些技术考虑到了立面解析问题的特殊性。具体来说，我们使用状态聚合来强制实施立面楼层的对称性，并展示如何使用 RL 在优化过程中利用基于图像的自下而上的指导。我们在巴黎建筑数据集上提供了系统的结果，并在以前方法所需时间的一小部分内获得了最先进的结果。我们在不同的成像条件下验证了我们的方法，并在线提供我们的软件和结果。
