![]() This was necessary for us to ensure that the neural net will correctly distinguish the style of the target’s gender. We also shared this data with the InsightFace gender detection model to verify the target subject’s gender. Although there are plenty of prepared photo datasets on the internet, they are not always suitable for a particular task like this or they may have poor image quality.įor quality control of target images, we used the RetinaFace neural net that allowed us to crop faces from high-quality images of human subjects for further editing. Our first task was to prepare a large dataset that contained numerous photos of people’s faces. The discriminator is rewarded for correctly determining if a photo was synthetically generated or not and the generator is rewarded for successfully “fooling” the discriminator. The generator’s task is to create an image that will suit our given parameters and the discriminator’s task is to decide if the image is generated by the network or not. During the training procedure, both of these components take part in the learning procedure by “competing” with each other. Generative adversarial network or GAN is a type of neural network that is composed of two different parts - generator and discriminator. ![]() In general, we tried to use generative adversarial networks in order to generate images of people with opposing genders. We tried a few novel techniques to train a Gender Swap GAN filter. Here, we are going to describe the methodology and approach that we used to develop this filter. The AI ArtDive application launched with Akvelon’s custom trained Gender Swap GAN filter that transforms the face of a subject in a photo to look like the opposite gender by altering their features to look more masculine or feminine. AI ArtDive is accessible via theses apps: web, iOS, and Android applications: ![]() In April 2020, Akvelon released AI ArtDive, an application that allows you to edit photos by applying AI-powered filters and effects.
0 Comments
Leave a Reply. |