Fast Video Object Segmentation by Reference-Guided Mask Propagation

Seoung Wug Oh, Joon-Young Lee, Kalyan Sunkavalli, Seon Joo Kim

CVPR 2018

This is the official demo code for the paper. PDF

Test Environment

Ubuntu
python 3.6
Pytorch 0.3.1
- installed with CUDA.

How to Run

Download DAVIS-2017.
Edit path for DAVIS_ROOT in run.py.

DAVIS_ROOT = '<Your DAVIS path>'

Download weights.pth and place it the same folde as run.py.
To run single-object video object segmentation on DAVIS-2016 validation.

python run.py

To run multi-object video object segmentation on DAVIS-2017 validation.

python run.py -MO

Results will be saved in ./results/SO or ./results/MO.

Train script

While our training script will not be released officially, xanderchf writes a great training script. Check it here:

https://github.com/xanderchf/RGMP

For pre-training, it is highly recommended to use recent large-scale Youtube-VOS dataset if you want to skip data synthesis from static images (Sect 3.2 in the paper) which is a headache.

Use

This software is for Non-commercial Research Purposes only.

If you use this code please cite:

@InProceedings{oh2018fast,
author = {Oh, Seoung Wug and Lee, Joon-Young and Sunkavalli, Kalyan and Kim, Seon Joo},
title = {Fast Video Object Segmentation by Reference-Guided Mask Propagation},
booktitle = {The IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
year = {2018}
}

Related Project

Please check out our NEW approach!

Video Object Segmentation using Space-Time Memory Networks
Seoung Wug Oh, Joon-Young Lee, Ning Xu, Seon Joo Kim
ICCV 2019

[paper] [github]

seoungwugoh / RGMP