Efficient 2D and 3D Facade Segmentation using Auto-Context

Raghudeep Gadde (1) , Varun Jampani (2) , Renaud Marlet (1, 3) , Peter Gehler (2, 4)

1 LIGM - Laboratoire d'Informatique Gaspard-Monge
2 Max Planck Institute for Intelligent Systems [Tübingen]
3 imagine [Marne-la-Vallée]
4 University of Tübingen

This paper introduces a fast and efficient segmentation technique for 2D images and 3D point clouds of building facades. Facades of buildings are highly structured and consequently most methods that have been proposed for this problem aim to make use of this strong prior information. Contrary to most prior work, we are describing a system that is almost domain independent and consists of standard segmentation methods. We train a sequence of boosted decision trees using auto-context features. This is learned using stacked generalization. We find that this technique performs better, or comparable with all previous published methods and present empirical results on all available 2D and 3D facade benchmark datasets. The proposed method is simple to implement, easy to extend, and very efficient at test-time inference.

Keywords: Stacked Generalization; Auto-Context; Facade Segmentation; Semantic Segmentation

Domains: Computer Vision and Pattern Recognition [cs.CV]

Raghudeep Gadde, Varun Jampani, Renaud Marlet, Peter Gehler. Efficient 2D and 3D Facade Segmentation using Auto-Context. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2018, 40 (5), pp.1273-1280. ⟨10.1109/TPAMI.2017.2696526⟩. ⟨hal-01743579⟩