부산대학교 도서관

It is still a great challenge in the Pose Transfer task to generate visually coherent images, to preserve the texture of clothes, to maintain the source identity and to realistically generate key human features such as the face or the hands. To tackle these challenges, we first conduct a study to obtain the most robust conditioning labels for this task and the baseline method [44] that we choose. We then improve upon the baseline by including deep source features from an Auto-encoder through an Attention mechanism. Finally we add region discriminators that are focused on key human features, thus obtaining results competitive with the state-of-the-art.