Reference Guided Reflection Removal Using Deep Visual Attribute Cues

The problem of air quality forecasting is important but also challenging because air quality is affected by a diverse set of complex factors. This paper describes the first image-based air quality forecasting model. It fuses a history of PM2.5 measurements with colocated images. Past research showed that images have the ability to inform on air quality in a region over time. We construct a multi-level attention-based recurrent network that uses images and PM2.5 data to represent variation over space and time. Experiments on Shanghai data show that our forecasting model improves PM2.5 prediction accuracy by 15.8% in RMSE and 10.9% in MAE compared to previous forecasting methods. in addition, we evaluate the impact of each model component via ablation studies.