Temporal Generative Adversarial Nets with Singular Value Clipping

Code

• github.com/universome/stylegan-v
  pytorch★ 391
• github.com/robbergen/trgan
  none★ 1
• github.com/pfnet-research/tgan2
  none★ 0
• github.com/pfnet-research/tgan
  none★ 0

Abstract

In this paper, we propose a generative model, Temporal Generative Adversarial Nets (TGAN), which can learn a semantic representation of unlabeled videos, and is capable of generating videos. Unlike existing Generative Adversarial Nets (GAN)-based methods that generate videos with a single generator consisting of 3D deconvolutional layers, our model exploits two different types of generators: a temporal generator and an image generator. The temporal generator takes a single latent variable as input and outputs a set of latent variables, each of which corresponds to an image frame in a video. The image generator transforms a set of such latent variables into a video. To deal with instability in training of GAN with such advanced networks, we adopt a recently proposed model, Wasserstein GAN, and propose a novel method to train it stably in an end-to-end manner. The experimental results demonstrate the effectiveness of our methods.

Tasks

Benchmark Results

Reproductions