liuguoyou / image-composition-of-partially-occluded-objects Goto Github PK
View Code? Open in Web Editor NEWThis paper solves the aforementioned challenges by proposing an efficient image composition method. Firstly, we extract the semantic contents of the images by using state-of-the-art deep learning methods. Therefore, the COI can be selected by only one click, which can greatly reduce the demanded user interactions.