Deep convolutional neural networks are used to address many computer vision problems, including video prediction. The task of video prediction requires analyzing the video frames, temporally and spatially, and constructing a model of how the environment evolves. Convolutional neural networks are spatially invariant, though, which prevents them from modeling location-dependent patterns. In this work, the authors propose location-biased convolutional layers to overcome this limitation. The effectiveness of location bias is evaluated on two architectures: Video Ladder Network (VLN) and Convolutional redictive Gating Pyramid (Conv-PGP). The results indicate that encoding location-dependent features is crucial for the task of video prediction. Our proposed methods significantly outperform spatially invariant models.
View on arXiv