Motion-Based Generator Model: Unsupervised Disentanglement of Appearance, Trackable and Intrackable Motions in Dynamic Patterns

Understand

Dynamic patterns are characterized by complex spatial and motion patterns.

• Understanding dynamic patterns requires a disentangled representational model that separates the factorial components.
• A commonly used model for dynamic patterns is the state space model, where the state evolves over time according to a transition model and the state generates the observed image frames according to an emission model.
• To model the motions explicitly, it is natural for the model to be based on the motions or the displacement fields of the pixels.