# High-Resolution Building and Road Detection from Sentinel-2

arXiv: https://arxiv.org/abs/2310.11622 · HTML: https://mlsanity.com/paper/2310.11622/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 23 references that are in the map.
- First posted on arXiv 17 Oct 2023.

## Builds on (most cited first, 9 of 9)

- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Image Super-Resolution via Iterative Refinement](https://mlsanity.com/paper/2104.07636/) (2021)
- [Objects as Points](https://mlsanity.com/paper/1904.07850/) (2019)
- [SatMAE: Pre-training Transformers for Temporal and Multi-Spectral Satellite Imagery](https://mlsanity.com/paper/2207.08051/) (2022)
- [Continental-Scale Building Detection from High Resolution Satellite Imagery](https://mlsanity.com/paper/2107.12283/) (2021)
- [HighRes-net: Recursive Fusion for Multi-Frame Super-Resolution of Satellite Imagery](https://mlsanity.com/paper/2002.06460/) (2020)
- [Permutation invariance and uncertainty in multitemporal image super-resolution](https://mlsanity.com/paper/2105.12409/) (2021)
- [On The Role of Alias and Band-Shift for Sentinel-2 Super-Resolution](https://mlsanity.com/paper/2302.11494/) (2023)
- [L1BSR: Exploiting Detector Overlap for Self-Supervised Single-Image Super-Resolution of Sentinel-2 L1B Imagery](https://mlsanity.com/paper/2304.06871/) (2023)

## Built on by (most cited first, 15 of 15)

- [PANGAEA: A Global and Inclusive Benchmark for Geospatial Foundation Models](https://mlsanity.com/paper/2412.04204/) (2024)
- [GlobalBuildingAtlas: An Open Global and Complete Dataset of Building Polygons, Heights and LoD1 3D Models](https://mlsanity.com/paper/2506.04106/) (2025)
- [High-resolution Population Maps Derived from Sentinel-1 and Sentinel-2](https://mlsanity.com/paper/2311.14006/) (2023)
- [TEMPO: Global Temporal Building Density and Height Estimation from Satellite Imagery](https://mlsanity.com/paper/2511.12104/) (2025)
- [GlobalBuildingMap -- Unveiling the Mystery of Global Buildings](https://mlsanity.com/paper/2404.13911/) (2024)
- [Joint Super-Resolution and Segmentation for 1-m Impervious Surface Area Mapping in China's Yangtze River Economic Belt](https://mlsanity.com/paper/2505.05367/) (2025)
- [GraphVSSM: Graph Variational State-Space Model for Probabilistic Spatiotemporal Inference of Dynamic Exposure and Vulnerability for Regional Disaster Resilience Assessment](https://mlsanity.com/paper/2508.01310/) (2025)
- [The Potential of Copernicus Satellites for Disaster Response: Retrieving Building Damage from Sentinel-1 and Sentinel-2](https://mlsanity.com/paper/2511.05461/) (2025)
- [SERA-H: Super-Resolution of Sentinel Time Series for Fine-Scale Canopy Height Mapping](https://mlsanity.com/paper/2512.18128/) (2025)
- [Local vs. Global: Local Land-Use and Land-Cover Models Deliver Higher Quality Maps](https://mlsanity.com/paper/2412.00777/) (2024)
- [GraphCSVAE: Graph Categorical Structured Variational Autoencoder for Spatiotemporal Auditing of Physical Vulnerability Towards Sustainable Post-Disaster Risk Reduction](https://mlsanity.com/paper/2509.10308/) (2025)
- [Predicting Household Water Consumption Using Satellite and Street View Images in Two Indian Cities](https://mlsanity.com/paper/2510.26957/) (2025)
- [VibrantSR: Sub-Meter Canopy Height Models from Sentinel-2 Using Generative Flow Matching](https://mlsanity.com/paper/2601.09866/) (2026)
- [Life Style Levels: Neighborhood Delineation using Geospatial Data](https://mlsanity.com/paper/2607.06529/) (2026)
- [A comparative assessment of global building and settlement datasets across geographic and settlement contexts](https://mlsanity.com/paper/2609.28154/) (2026)

## Abstract (arXiv)

Mapping buildings and roads automatically with remote sensing typically requires high-resolution imagery, which is expensive to obtain and often sparsely available. In this work we demonstrate how multiple 10 m resolution Sentinel-2 images can be used to generate 50 cm resolution building and road segmentation masks. This is done by training a `student' model with access to Sentinel-2 images to reproduce the predictions of a `teacher' model which has access to corresponding high-resolution imagery. While the predictions do not have all the fine detail of the teacher model, we find that we are able to retain much of the performance: for building segmentation we achieve 79.0% mIoU, compared to the high-resolution teacher model accuracy of 85.5% mIoU. We also describe two related methods that work on Sentinel-2 imagery: one for counting individual buildings which achieves R2 = 0.91 against true counts and one for predicting building height with 1.5 meter mean absolute error. This work opens up new possibilities for using freely available Sentinel-2 imagery for a range of tasks that previously could only be done with high-resolution satellite imagery.