Compositional GAN: Learning Image-Conditional Binary Composition

19 Jul 2018  ·  Samaneh Azadi, Deepak Pathak, Sayna Ebrahimi, Trevor Darrell ·

Generative Adversarial Networks (GANs) 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, including their relative scaling, spatial layout, occlusion, or viewpoint transformation is a challenging problem. In this work, we propose a novel self-consistent Composition-by-Decomposition (CoDe) network to compose a pair of objects. Given object images from two distinct distributions, our model can generate a realistic composite image from their joint distribution following the texture and shape of the input objects. We evaluate our approach through qualitative experiments and user evaluations. Our results indicate that the learned model captures potential interactions between the two object domains, and generates realistic composed scenes at test time.

PDF Abstract

Results from the Paper

  Submit results from this paper to get state-of-the-art GitHub badges and help the community compare results to other papers.


No methods listed for this paper. Add relevant methods here