DAGAN: A Domain-Aware Method for Image-to-Image Translations

<div>Background translations. This figure shows translation generations (Cityscapes <svg height="6.27169pt" id="M134" style="vertical-align:-0.04980993pt" version="1.1" viewbox="-0.0498162 -6.22188 22.8176 6.27169" width="22.8176pt" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink"><g transform="matrix(.013,0,0,-0.013,0,0)"><path d="M885 230V280H158L260 427L238 442C164 361 93 290 53 255C93 220 164 149 238 68L260 83L158 230H885Z"></path></g><g transform="matrix(.013,0,0,-0.013,10.223,0)"><path d="M901 255C861 290 790 361 716 442L694 427L796 280H69V230H796L694 83L716 68C790 149 861 220 901 255Z"></path></g></svg> GTA) from the background network. Inputs from both datasets are shown in the first and third column, and the outputs are shown in the second and fourth row. (a) Cityscapes. (b) GTA.</div>

Complexity

DAGAN: A Domain-Aware Method for Image-to-Image Translations

Figure 9