Conditional High-Resolution Image Synthesizing Based on Generative Adversarial Networks

• Main Authors: Ting-Jia Yang, 楊庭嘉
• Other Authors: Nai-Jian Wang
• Format: Others
• Language: en_US
• Published: 2018
• Online Access: http://ndltd.ncl.edu.tw/handle/my7yyw

碩士 === 國立臺灣科技大學 === 電機工程系 === 106 === We present a conditional high resolution image generating system that can synthesize face images based on input of a wide range of facial attributes. First we focus on the training and optimization of an image generation model that synthe sizes high resolution images based on the Wasserstein distance and progressive growing method. Then to exert control over the image generation model, we deviate from the current trend and instead explore the viability of augmenting the image generation model by introducing a second generative adversarial network that learns its conditional latent space distribution in hope to manipulate the attributes of its output images. Experiments were conducted on CelebA and MNIST dataset. Results show that our method can convert an existing generative model to a conditional generative model that synthesize images based on input class or attributes while retaining reasonable diversity. Furthermore, this method allows one to incorporate labels from multiple datasets without retraining the generative model from scratch.