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

By Raghudeep Gadde, Varun Jampani, Renaud Marlet, Peter Gehler. 2016

73 citations recorded by the source corpus.

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.

Subfields: Civil and Structural Engineering, Environmental Engineering, Geology

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Civil and Structural Engineering

1. Andreas Geiger

In Environmental Engineering

1. Andreas Geiger
2. Ali O. Ulusoy
3. Fatma Güney
4. Joel Janai
5. Aseem Behl
6. Gernot Riegler
7. Michael J. Black

In Geology

1. Joel Janai
2. Aseem Behl
3. Ali O. Ulusoy
4. Fatma Güney
5. Gernot Riegler
6. Andreas Geiger

Citations in the corpus

• OctNet: Learning Deep 3D Representations at High Resolutions (2016, methodology): “Table 1 compares the proposed OctNet to several state of the art approaches on the facade labeling task following the extended evaluation protocol of [12].”
• Computer Vision for Autonomous Vehicles: Problems, Datasets and State-of-the-Art (2017, methodology): “Inspired by higher order CRFs for semantic segmentation, Gadde et al. (2016a) propose a new Bilateral Inception module for CNN architectures as an alternative to structured CNNs and CRF techniques.”