Learning to Generate Chairs with Generative Adversarial Nets
This work addresses a specific bottleneck in GAN training for computer vision researchers, offering incremental improvements in model design.
The authors tackled the challenge of training convolutional GANs with fully-connected hidden layers, which was previously limited due to optimization complexities, and they proposed architectural modifications that enabled more powerful GAN models, demonstrating effectiveness in synthesizing 3D object projections with interpolation capabilities.
Generative adversarial networks (GANs) has gained tremendous popularity lately due to an ability to reinforce quality of its predictive model with generated objects and the quality of the generative model with and supervised feedback. GANs allow to synthesize images with a high degree of realism. However, the learning process of such models is a very complicated optimization problem and certain limitation for such models were found. It affects the choice of certain layers and nonlinearities when designing architectures. In particular, it does not allow to train convolutional GAN models with fully-connected hidden layers. In our work, we propose a modification of the previously described set of rules, as well as new approaches to designing architectures that will allow us to train more powerful GAN models. We show the effectiveness of our methods on the problem of synthesizing projections of 3D objects with the possibility of interpolation by class and view point.