# CrevNet: Conditionally Reversible Video Prediction

arXiv: https://arxiv.org/abs/1910.11577 · HTML: https://mlsanity.com/paper/1910.11577/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 25 Oct 2019.

## Built on by (most cited first, 15 of 15)

- [MMVP: Motion-Matrix-based Video Prediction](https://mlsanity.com/paper/2308.16154/) (2023)
- [MIMO Is All You Need : A Strong Multi-In-Multi-Out Baseline for Video Prediction](https://mlsanity.com/paper/2212.04655/) (2022)
- [Traffic4cast at NeurIPS 2021 -- Temporal and Spatial Few-Shot Transfer Learning in Gridded Geo-Spatial Processes](https://mlsanity.com/paper/2203.17070/) (2022)
- [Implicit Stacked Autoregressive Model for Video Prediction](https://mlsanity.com/paper/2303.07849/) (2023)
- [Learning to Transfer for Traffic Forecasting via Multi-task Learning](https://mlsanity.com/paper/2111.15542/) (2021)
- [Video RWKV:Video Action Recognition Based RWKV](https://mlsanity.com/paper/2411.05636/) (2024)
- [SwinUNet3D -- A Hierarchical Architecture for Deep Traffic Prediction using Shifted Window Transformers](https://mlsanity.com/paper/2201.06390/) (2022)
- [Rethinking Urban Mobility Prediction: A Super-Multivariate Time Series Forecasting Approach](https://mlsanity.com/paper/2312.01699/) (2023)
- [An Efficient Two-stage Gradient Boosting Framework for Short-term Traffic State Estimation](https://mlsanity.com/paper/2302.10400/) (2023)
- [Masked Autoregressive Model for Weather Forecasting](https://mlsanity.com/paper/2409.20117/) (2024)
- [Real-time Video Prediction With Fast Video Interpolation Model and Prediction Training](https://mlsanity.com/paper/2503.23185/) (2025)
- [See the past: Time-Reversed Scene Reconstruction from Thermal Traces Using Visual Language Models](https://mlsanity.com/paper/2510.05408/) (2025)
- [From Single to Multiple: Leveraging Multi-level Prediction Spaces for Video Forecasting](https://mlsanity.com/paper/2107.10068/) (2021)
- [Enabling Real-time Neural Recovery for Cloud Gaming on Mobile Devices](https://mlsanity.com/paper/2307.07847/) (2023)
- [Time-Reversed Imaging: A Multimodal Benchmark and Framework for Reconstructing Past Human-Environment Interactions](https://mlsanity.com/paper/2607.22352/) (2026)

## Abstract (arXiv)

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.