# PM25Vision: A Large-Scale Benchmark Dataset for Visual Estimation of Air Quality

arXiv: https://arxiv.org/abs/2509.16519 · HTML: https://mlsanity.com/paper/2509.16519/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 5 of its 11 references that are in the map.
- First posted on arXiv 20 Sep 2025.

## Builds on (most cited first, 5 of 5)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [Uncovering local aggregated air quality index with smartphone captured images leveraging efficient deep convolutional neural network](https://mlsanity.com/paper/2308.03200/) (2023)
- [HVAQ: A High-Resolution Vision-Based Air Quality Dataset](https://mlsanity.com/paper/2102.09332/) (2021)

## Built on by (most cited first, 1 of 1)

- [M2FedAQI: Multimodal Federated Learning for Air Quality Prediction on Heterogeneous Edge Devices](https://mlsanity.com/paper/2605.16375/) (2026)

## Abstract (arXiv)

We introduce PM25Vision (PM25V), the largest and most comprehensive dataset to date for estimating air quality - specifically PM2.5 concentrations - from street-level images. The dataset contains over 11,114 images matched with timestamped and geolocated PM2.5 readings across 3,261 AQI monitoring stations and 11 years, significantly exceeding the scale of previous benchmarks. The spatial accuracy of this dataset has reached 5 kilometers, far exceeding the city-level accuracy of many datasets. We describe the data collection, synchronization, and cleaning pipelines, and provide baseline model performances using CNN and transformer architectures. Our dataset is publicly available.