Deep Structured Generative Models
This addresses the challenge of generating structured images for computer vision applications, representing an incremental improvement by combining existing methods with structure information.
The paper tackles the problem of generating images with complex structures by proposing a deep structured generative model that integrates stochastic and-or graphs (sAOG) with GANs to capture spatial layouts and semantic relations, resulting in improved modeling and realistic image generation as demonstrated in experiments.
Deep generative models have shown promising results in generating realistic images, but it is still non-trivial to generate images with complicated structures. The main reason is that most of the current generative models fail to explore the structures in the images including spatial layout and semantic relations between objects. To address this issue, we propose a novel deep structured generative model which boosts generative adversarial networks (GANs) with the aid of structure information. In particular, the layout or structure of the scene is encoded by a stochastic and-or graph (sAOG), in which the terminal nodes represent single objects and edges represent relations between objects. With the sAOG appropriately harnessed, our model can successfully capture the intrinsic structure in the scenes and generate images of complicated scenes accordingly. Furthermore, a detection network is introduced to infer scene structures from a image. Experimental results demonstrate the effectiveness of our proposed method on both modeling the intrinsic structures, and generating realistic images.