Applying resolution-preserving blocks is a common practice to maximize information preservation in video prediction, yet their high memory consumption greatly limits their application scenarios. We propose CrevNet, a Conditionally Reversible Network that uses reversible architectures to build a bijective two-way autoencoder and its complementary recurrent predictor. Our model enjoys the theoretically guaranteed property of no information loss during the feature extraction, much lower memory consumption and computational efficiency.
@article{arxiv.1910.11577,
title = {CrevNet: Conditionally Reversible Video Prediction},
author = {Wei Yu and Yichao Lu and Steve Easterbrook and Sanja Fidler},
journal= {arXiv preprint arXiv:1910.11577},
year = {2019}
}