English

Video Pixel Networks

Computer Vision and Pattern Recognition 2016-10-05 v1 Machine Learning

Abstract

We propose a probabilistic video model, the Video Pixel Network (VPN), that estimates the discrete joint distribution of the raw pixel values in a video. The model and the neural architecture reflect the time, space and color structure of video tensors and encode it as a four-dimensional dependency chain. The VPN approaches the best possible performance on the Moving MNIST benchmark, a leap over the previous state of the art, and the generated videos show only minor deviations from the ground truth. The VPN also produces detailed samples on the action-conditional Robotic Pushing benchmark and generalizes to the motion of novel objects.

Keywords

Cite

@article{arxiv.1610.00527,
  title  = {Video Pixel Networks},
  author = {Nal Kalchbrenner and Aaron van den Oord and Karen Simonyan and Ivo Danihelka and Oriol Vinyals and Alex Graves and Koray Kavukcuoglu},
  journal= {arXiv preprint arXiv:1610.00527},
  year   = {2016}
}

Comments

16 pages

R2 v1 2026-06-22T16:08:43.743Z