← Search

Taufik Xu

2 accepted papers

2019

Multi-objects Generation with Amortized Structural Regularization

NeurIPS 2019poster

Deep generative models (DGMs) have shown promise in image generation. However, most of the existing methods learn a model by simply optimizing a divergence between the marginal distributions of the model and the data, and often fail to capture rich structures, such as attributes of objects and their…