Video Prediction with Appearance and Motion Conditions
arXiv:1807.02635
Abstract
Video prediction aims to generate realistic future frames by learning dynamic visual patterns. One fundamental challenge is to deal with future uncertainty: How should a model behave when there are multiple correct, equally probable future? We propose an Appearance-Motion Conditional GAN to address this challenge. We provide appearance and motion information as conditions that specify how the future may look like, reducing the level of uncertainty. Our model consists of a generator, two discriminators taking charge of appearance and motion pathways, and a perceptual ranking module that encourages videos of similar conditions to look similar. To train our model, we develop a novel conditioning scheme that consists of different combinations of appearance and motion conditions. We evaluate our model using facial expression and human action datasets and report favorable results compared to existing methods.
arXiv commentAccepted paper at ICML 2018. Project page: http://vision.snu.ac.kr/projects/amc-gan
Cited by in corpus (4)
- InMoDeGAN: Interpretable Motion Decomposition Generative Adversarial Network for Video Generation
- Transformation-based Adversarial Video Prediction on Large-Scale Data
- Ebola Optimization Search Algorithm (EOSA): A new metaheuristic algorithm based on the propagation model of Ebola virus disease
- Adversarial Framework for Unsupervised Learning of Motion Dynamics in Videos