# Video Extrapolation with an Invertible Linear Embedding

arXiv: https://arxiv.org/abs/1903.00133 · HTML: https://mlsanity.com/paper/1903.00133/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 Mar 2019.

## Built on by (most cited first, 2 of 2)

- [Towards Efficient Real-Time Video Motion Transfer via Generative Time Series Modeling](https://mlsanity.com/paper/2504.05537/) (2025)
- [Wide and Narrow: Video Prediction from Context and Motion](https://mlsanity.com/paper/2110.11586/) (2021)

## Abstract (arXiv)

We predict future video frames from complex dynamic scenes, using an invertible neural network as the encoder of a nonlinear dynamic system with latent linear state evolution. Our invertible linear embedding (ILE) demonstrates successful learning, prediction and latent state inference. In contrast to other approaches, ILE does not use any explicit reconstruction loss or simplistic pixel-space assumptions. Instead, it leverages invertibility to optimize the likelihood of image sequences exactly, albeit indirectly. Comparison with a state-of-the-art method demonstrates the viability of our approach.