albert100121 / MLVR-Pytorch

A Pytorch implementation of The Visual Centrifuge: Model-Free Layered Video Representations.

DispNet Pytorch

Overview

This is a pytorch implementation of The Visual Centrifuge: Model-Free Layered Video Representations in CVPR 2019.

Model Architecture

Predictor-Corrector Architecture

UNet

Usage

from MLVR import MLVR
...
model = MLVR()

Citation

@inproceedings{alayrac2019visual,
  title={The visual centrifuge: Model-free layered video representations},
  author={Alayrac, Jean-Baptiste and Carreira, Joao and Zisserman, Andrew},
  booktitle={Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition},
  pages={2457--2466},
  year={2019}
}