Dayton

Introduced by Vo et al. in Localizing and Orienting Street Views Using Overhead Imagery

The Dayton dataset is a dataset for ground-to-aerial (or aerial-to-ground) image translation, or cross-view image synthesis. It contains images of road views and aerial views of roads. There are 76,048 images in total and the train/test split is 55,000/21,048. The images in the original dataset have 354×354 resolution.

Source: Multi-Channel Attention Selection GANs for Guided Image-to-Image Translation

Homepage

Benchmarks

Add a new result Link an existing benchmark

Task	Dataset Variant	Best Model
Cross-View Image-to-Image Translation	Dayton (256×256) - aerial-to-ground	SelectionGAN
Cross-View Image-to-Image Translation	Dayton (64×64) - aerial-to-ground	SelectionGAN
Cross-View Image-to-Image Translation	Dayton (64x64) - ground-to-aerial	SelectionGAN
Cross-View Image-to-Image Translation	Dayton (256×256) - ground-to-aerial	SelectionGAN