# TorontoCity: Seeing the World with a Million Eyes

arXiv: https://arxiv.org/abs/1612.00423 · HTML: https://mlsanity.com/paper/1612.00423/

## Key facts

- Cited by 24 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 Dec 2016.

## Built on by (most cited first, 24 of 24)

- [VectorMapNet: End-to-end Vectorized HD Map Learning](https://mlsanity.com/paper/2206.08920/) (2022)
- [Neural Map Prior for Autonomous Driving](https://mlsanity.com/paper/2304.08481/) (2023)
- [A Survey on Autonomous Driving Datasets: Statistics, Annotation Quality, and a Future Outlook](https://mlsanity.com/paper/2401.01454/) (2024)
- [Semantics for Robotic Mapping, Perception and Interaction: A Survey](https://mlsanity.com/paper/2101.00443/) (2021)
- [Capturing Omni-Range Context for Omnidirectional Segmentation](https://mlsanity.com/paper/2103.05687/) (2021)
- [Trust, but Verify: Cross-Modality Fusion for HD Map Change Detection](https://mlsanity.com/paper/2212.07312/) (2022)
- [OmniCity: Omnipotent City Understanding with Multi-level and Multi-view Images](https://mlsanity.com/paper/2208.00928/) (2022)
- [MCD: Diverse Large-Scale Multi-Campus Dataset for Robot Perception](https://mlsanity.com/paper/2403.11496/) (2024)
- [High-Definition Map Generation Technologies For Autonomous Driving](https://mlsanity.com/paper/2206.05400/) (2022)
- [A Survey on Approximate Edge AI for Energy Efficient Autonomous Driving Services](https://mlsanity.com/paper/2304.14271/) (2023)
- [Pix2Map: Cross-modal Retrieval for Inferring Street Maps from Images](https://mlsanity.com/paper/2301.04224/) (2023)
- [4Seasons: Benchmarking Visual SLAM and Long-Term Localization for Autonomous Driving in Challenging Conditions](https://mlsanity.com/paper/2301.01147/) (2022)
- [PathwayBench: Assessing Routability of Pedestrian Pathway Networks Inferred from Multi-City Imagery](https://mlsanity.com/paper/2407.16875/) (2024)
- [APE: An Open and Shared Annotated Dataset for Learning Urban Pedestrian Path Networks](https://mlsanity.com/paper/2303.02323/) (2023)
- [Object Recognition Datasets and Challenges: A Review](https://mlsanity.com/paper/2507.22361/) (2025)
- [PanorAMS: Automatic Annotation for Detecting Objects in Urban Context](https://mlsanity.com/paper/2208.14295/) (2022)
- [Mastering Spatial Graph Prediction of Road Networks](https://mlsanity.com/paper/2210.00828/) (2022)
- [Building Footprint Extraction with Graph Convolutional Network](https://mlsanity.com/paper/2305.04499/) (2023)
- [TFNet: Tuning Fork Network with Neighborhood Pixel Aggregation for Improved Building Footprint Extraction](https://mlsanity.com/paper/2311.02617/) (2023)
- [Fine-Grained Building Function Recognition from Street-View Images via Geometry-Aware Semi-Supervised Learning](https://mlsanity.com/paper/2408.09460/) (2024)
- [Self-Supervised Pretraining for Aerial Road Extraction](https://mlsanity.com/paper/2503.24326/) (2025)
- [DOGE: Differentiable Bezier Graph Optimization for Road Network Extraction](https://mlsanity.com/paper/2511.19850/) (2025)
- [Delaunay Canopy: Building Wireframe Reconstruction from Airborne LiDAR Point Clouds via Delaunay Graph](https://mlsanity.com/paper/2604.02497/) (2026)
- [GOLD-BEV: GrOund and aeriaL Data for Dense Semantic BEV Mapping of Dynamic Scenes](https://mlsanity.com/paper/2604.19411/) (2026)

## Abstract (arXiv)

In this paper we introduce the TorontoCity benchmark, which covers the full greater Toronto area (GTA) with 712.5 km2 of land, 8439 km of road and around 400,000 buildings. Our benchmark provides different perspectives of the world captured from airplanes, drones and cars driving around the city. Manually labeling such a large scale dataset is infeasible. Instead, we propose to utilize different sources of high-precision maps to create our ground truth. Towards this goal, we develop algorithms that allow us to align all data sources with the maps while requiring minimal human supervision. We have designed a wide variety of tasks including building height estimation (reconstruction), road centerline and curb extraction, building instance segmentation, building contour extraction (reorganization), semantic labeling and scene type classification (recognition). Our pilot study shows that most of these tasks are still difficult for modern convolutional neural networks.