Teodora SuciuinGenerate visionThe #paperoftheweek is: “Generating Diverse High-Fidelity Images with VQ-VAE-2”In our weekly paper, the authors propose a two-stage generator architecture which aims to exploit the strengths of two separate generative…Jul 3, 20191Jul 3, 20191
Teodora SuciuGeometry-Contrastive GAN for Facial Expression TransferIn this paper, we propose a Geometry-Contrastive Generative Adversarial Network (GC-GAN) for transferring continuous emotions across…Nov 9, 2018Nov 9, 2018