High Resolution Daytime Translation Without Domain Labels
Gallery 5:53 Modeling daytime changes in highresolution photographs, e. g., rerendering the same scene under different illuminations typical for day, night, or dawn, is a challenging image manipulation task. We present the highresolution daytime translation (HiDT) model for this task. HiDT combines a generative imagetoimage model and a new upsampling scheme that allows to apply image translation at high resolution. The model demonstrates competitive results in terms of both commonly used GAN metrics a
|
|