# Structured Outdoor Architecture Reconstruction by Exploration and Classification

arXiv: https://arxiv.org/abs/2108.07990 · HTML: https://mlsanity.com/paper/2108.07990/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 24 references that are in the map.
- First posted on arXiv 18 Aug 2021.

## Builds on (most cited first, 16 of 16)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [Deep Reinforcement Learning with Double Q-learning](https://mlsanity.com/paper/1509.06461/) (2015)
- [Efficient Interactive Annotation of Segmentation Datasets with Polygon-RNN++](https://mlsanity.com/paper/1803.09693/) (2018)
- [Write, Execute, Assess: Program Synthesis with a REPL](https://mlsanity.com/paper/1906.04604/) (2019)
- [Annotating Object Instances with a Polygon-RNN](https://mlsanity.com/paper/1704.05548/) (2017)
- [PlaneNet: Piece-wise Planar Reconstruction from a Single RGB Image](https://mlsanity.com/paper/1804.06278/) (2018)
- [End-to-End Wireframe Parsing](https://mlsanity.com/paper/1905.03246/) (2019)
- [Single-Image Piece-wise Planar 3D Reconstruction via Associative Embedding](https://mlsanity.com/paper/1902.09777/) (2019)
- [PPGNet: Learning Point-Pair Graph for Line Segment Detection](https://mlsanity.com/paper/1905.03415/) (2019)
- [Floor-SP: Inverse CAD for Floorplans by Sequential Room-wise Shortest Path](https://mlsanity.com/paper/1908.06702/) (2019)
- [DARNet: Deep Active Ray Network for Building Segmentation](https://mlsanity.com/paper/1905.05889/) (2019)
- [Conv-MPN: Convolutional Message Passing Neural Network for Structured Outdoor Architecture Reconstruction](https://mlsanity.com/paper/1912.01756/) (2019)
- [Modeling 3D Shapes by Reinforcement Learning](https://mlsanity.com/paper/2003.12397/) (2020)
- [Vectorizing World Buildings: Planar Graph Reconstruction by Primitive Detection and Relationship Inference](https://mlsanity.com/paper/1912.05135/) (2019)

## Built on by (most cited first, 6 of 6)

- [HEAT: Holistic Edge Attention Transformer for Structured Reconstruction](https://mlsanity.com/paper/2111.15143/) (2021)
- [PolyRoom: Room-aware Transformer for Floorplan Reconstruction](https://mlsanity.com/paper/2407.10439/) (2024)
- [Optimized Vectorizing of Building Structures with Switch: High-Efficiency Convolutional Channel-Switch Hybridization Strategy](https://mlsanity.com/paper/2306.15035/) (2023)
- [CornerFormer: Boosting Corner Representation for Fine-Grained Structured Reconstruction](https://mlsanity.com/paper/2304.07072/) (2023)
- [Holistic Geometric Feature Learning for Structured Reconstruction](https://mlsanity.com/paper/2309.09622/) (2023)
- [Unsupervised Roofline Extraction from True Orthophotos for LoD2 Building Model Reconstruction](https://mlsanity.com/paper/2310.01067/) (2023)

## Abstract (arXiv)

This paper presents an explore-and-classify framework for structured architectural reconstruction from an aerial image. Starting from a potentially imperfect building reconstruction by an existing algorithm, our approach 1) explores the space of building models by modifying the reconstruction via heuristic actions; 2) learns to classify the correctness of building models while generating classification labels based on the ground-truth, and 3) repeat. At test time, we iterate exploration and classification, seeking for a result with the best classification score. We evaluate the approach using initial reconstructions by two baselines and two state-of-the-art reconstruction algorithms. Qualitative and quantitative evaluations demonstrate that our approach consistently improves the reconstruction quality from every initial reconstruction.