# Polygonizer: An auto-regressive building delineator

arXiv: https://arxiv.org/abs/2304.04048 · HTML: https://mlsanity.com/paper/2304.04048/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 17 references that are in the map.
- First posted on arXiv 8 Apr 2023.

## Builds on (most cited first, 8 of 8)

- [Neural Machine Translation by Jointly Learning to Align and Translate](https://mlsanity.com/paper/1409.0473/) (2014)
- [Random Erasing Data Augmentation](https://mlsanity.com/paper/1708.04896/) (2017)
- [Efficient Interactive Annotation of Segmentation Datasets with Polygon-RNN++](https://mlsanity.com/paper/1803.09693/) (2018)
- [Topological Map Extraction from Overhead Images](https://mlsanity.com/paper/1812.01497/) (2018)
- [Polygonal Building Segmentation by Frame Field Learning](https://mlsanity.com/paper/2004.14875/) (2020)
- [ESFNet: Efficient Network for Building Extraction from High-Resolution Aerial Images](https://mlsanity.com/paper/1903.12337/) (2019)
- [PolyBuilding: Polygon Transformer for End-to-End Building Extraction](https://mlsanity.com/paper/2211.01589/) (2022)
- [Automatic Building Extraction in Aerial Scenes Using Convolutional Networks](https://mlsanity.com/paper/1602.06564/) (2016)

## Built on by (most cited first, 3 of 3)

- [HiT: Building Mapping with Hierarchical Transformers](https://mlsanity.com/paper/2309.09643/) (2023)
- [RoIPoly: Vectorized Building Outline Extraction Using Vertex and Logit Embeddings](https://mlsanity.com/paper/2407.14920/) (2024)
- [GeoFormer: A Multi-Polygon Segmentation Transformer](https://mlsanity.com/paper/2411.16616/) (2024)

## Abstract (arXiv)

In geospatial planning, it is often essential to represent objects in a vectorized format, as this format easily translates to downstream tasks such as web development, graphics, or design. While these problems are frequently addressed using semantic segmentation, which requires additional post-processing to vectorize objects in a non-trivial way, we present an Image-to-Sequence model that allows for direct shape inference and is ready for vector-based workflows out of the box. We demonstrate the model's performance in various ways, including perturbations to the image input that correspond to variations or artifacts commonly encountered in remote sensing applications. Our model outperforms prior works when using ground truth bounding boxes (one object per image), achieving the lowest maximum tangent angle error.