2 papers
cs.CV2023
Trained Latent Space Navigation to Prevent Lack of Photorealism in Generated Images on Style-based Models
Takumi Harada, Kazuyuki Aihara, Hiroyuki Sakai
Recent studies on StyleGAN variants show promising performances for various generation tasks. In these models, latent codes have traditionally been manipulated and searched for the…
cs.CV2023
Feature representations useful for predicting image memorability
Takumi Harada, Hiroyuki Sakai
Prediction of image memorability has attracted interest in various fields. Consequently, the prediction accuracy of convolutional neural network (CNN) models has been approaching t…