In this recipe, we're going to cover a few basic techniques for producing 3D models with GANs and we'll see how we can simplify these architectures for learning.
Introduction to using GANs in order to produce 3D models
Getting ready
There are three papers that you'll need to review to understand this recipe:
- Learning a Probabilistic Latent Space of Object Shapes via 3D Generative-Adversarial Modeling:Â http://3dgan.csail.mit.edu/papers/3dgan_nips.pdf.
- Learning Shape Priors for Single-View 3D Completion and Reconstruction:Â http://shapehd.csail.mit.edu/papers/shapehd_eccv.pdf.
- Interactive 3D Modeling with a Generative Adversarial Network:Â https://arxiv.org/pdf/1706.05170.pdf.