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

arXiv: https://arxiv.org/abs/1606.06437 · HTML: https://mlsanity.com/paper/1606.06437/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 21 Jun 2016.

## Built on by (most cited first, 10 of 10)

- [Bidirectional Projection Network for Cross Dimension Scene Understanding](https://mlsanity.com/paper/2103.14326/) (2021)
- [Objects Can Move: 3D Change Detection by Geometric Transformation Constistency](https://mlsanity.com/paper/2208.09870/) (2022)
- [Improving Facade Parsing with Vision Transformers and Line Integration](https://mlsanity.com/paper/2309.15523/) (2023)
- [Has Anything Changed? 3D Change Detection by 2D Segmentation Masks](https://mlsanity.com/paper/2312.01148/) (2023)
- [Dynamic Convolution for 3D Point Cloud Instance Segmentation](https://mlsanity.com/paper/2107.08392/) (2021)
- [Semi-Supervised Adversarial Recognition of Refined Window Structures for Inverse Procedural Faccade Modeling](https://mlsanity.com/paper/2201.08977/) (2022)
- [Semantic Image Translation for Repairing the Texture Defects of Building Models](https://mlsanity.com/paper/2303.17418/) (2023)
- [StructuredMesh: 3D Structured Optimization of Faccade Components on Photogrammetric Mesh Models using Binary Integer Programming](https://mlsanity.com/paper/2306.04184/) (2023)
- [Deep Learning-based Scalable Image-to-3D Facade Parser for Generating Thermal 3D Building Models](https://mlsanity.com/paper/2508.04406/) (2025)
- [Facade Segmentation for Solar Photovoltaic Suitability](https://mlsanity.com/paper/2511.18882/) (2025)

## Abstract (arXiv)

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.