Compositional GAN: Learning Image-Conditional Binary Composition
International Journal of Computer Vision, pp. 2570-2585, 2019.
Generative Adversarial Networks can produce images of remarkable complexity and realism but are generally structured to sample from a single latent source ignoring the explicit spatial interaction between multiple entities that could be present in a scene. Capturing such complex interactions between different objects in the world, includi...More
PPT (Upload PPT)