CONTEXT-AWARE NATURAL INTEGRATION OF ADVERTISEMENT OBJECT

Product placement, also called advertisement embedding, is to place some specific products in an image or a video, which may attract consumers to buy their products. However, adding advertisement objects in images is difficult, because where to add the product and how to fuse the background must be concerned. In this paper, to overcome this issue, we present a novel hierarchical framework with conditional generative adversarial network to add advertisement object in all kinds of scene images. The key point of our framework is leaning the relation between surrounding and products. To generate the products more realistic and to make the detail information such characters and logo more clear, we propose local-global discriminator. Our experiment demonstrates the effectiveness of our proposed method on different scene images. Detail codes and results are available in GitHub. https://github.com/happyyuwei/ProductPlacement