Papers with Code · CC BY-SA 4.0
Image-to-Image Translation
Image-to-Image Translation is a task in computer vision and machine learning where the goal is to learn a mapping between an input image and an output image, such that the output image can be used to perform a specific task, such as style transfer, data augmentation, or image restoration.
<span style="color:grey; opacity: 0.6">( Image credit: Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks )</span>
데이터셋
62개horse2zebraselfie2animeCats-and-DogsEPFL NIR-VISFreiburg Forest Datasetphoto2vangoghvangogh2photozebra2horseAerial-to-MapDeep-FashionObject Transfiguration (sheep-to-giraffe)SYNTHIA Fall-to-WinterSYNTHIA-to-Cityscapes Labelsanime-to-selfieselfie-to-anime2017_test setADE-Indoor Labels-to-PhotoAFHQAFHQ (Cat to Dog)AFHQ (Wild to Dog)Apples and OrangesBRATSCPM-Synt-1CPM-Synt-2CVACTCam2BEVKITTI Object Tracking Evaluation 2012VITON-HDZebra and Horsesdog2cat