Deepfakes: Face synthesis with GANs and Autoencoders
A closer look on Deepfakes: face sythesis with StyleGAN, face swap with XceptionNet and facial attributes and expression manipulation with StarGAN
The fifth article-series of GAN in computer vision - we discuss self-supervision in adversarial training for unconditional image generation as well as in-layer normalization and style incorporation in high-resolution image synthesis.
The fourth article-series of GAN in computer vision - we explore 2K image generation with a multi-scale GAN approach, video synthesis with temporal consistency, and large-scale class-conditional image generation in ImageNet.
The third article-series of GAN in computer vision - we encounter some of the most advanced training concepts such as Wasserstein distance, adopt a game theory aspect in the training of GAN, and study the incremental/progressive generative training to reach a megapixel resolution.
The second article of the GANs in computer vision series - looking deeper in generative adversarial networks, mode collapse, conditional image synthesis, and 3D object generation, paired and unpaired image to image generation.