Guided Interactive Video Object Segmentation Using Reliability-Based Attention Maps
Yuk Heo, Yeong Jun Koh, Chang-Su Kim
Implementation of CVPR2021 oral paper (best paper candidate), "Guided Interactive Video Object Segmentation Using Reliability-Based Attention Maps"
[Paper] [Project page] [Video-introduction] [Video-comparison]
Codes in this github:
- DAVIS2017 evaluation based on the DAVIS framework
- Youtube-iVOS evaluation based on the Youtube2019
- DAVIS2017 real-world evaluation GUI - linked to GUI-iVOS_and_GIS
Prerequisite
- cuda 11.0
- python 3.6
- pytorch 1.6.0
- davisinteractive 1.0.4
- numpy, cv2, PtQt5, and other general libraries of python3
Directory Structure
-
root/checkpoints: save our checkpoints (pth extensions) here. -
root/dataset_torch: pytorch datasets. -
root/libs: library of utility files. -
root/networks: codes for networksdeeplab: applies ASPP module in decoders. [original code]network.py: consists our whole network.
-
root/results: result files for both evaluation results are attached. -
root/config.py: configurations. you must set your directories here. -
root/IVOS_main_DAVIS.py: DAVIS2017 evaluation based on the DAVIS framework. -
root/IVOS_main_youtube.py: Youtube-iVOS evaluation based on the Youtube2019.
Instruction
DAVIS2017 evaluation based on the DAVIS framework
-
Edit
config.pyto set the directory of your DAVIS2017 dataset and the other configurations. -
Download our parameters and place the file as
root/checkpoints/GIS-ckpt_standard.pth.- For DAVIS2017 evaluation [Google-Drive]
- For youtube2019 evaluation [Google-Drive]
-
Evaluate with
python3 IVOS_main_DAVIS.py.python3 IVOS_main_youtube.py.
DAVIS2017 real-world evaluation GUI
Multi-object GUI (for DAVIS2017) is available at our github page, [GUI-IVOS]
Reference
Please cite our paper if the implementations are useful in your work:
@Inproceedings{
Yuk2021GIS,
title={Guided Interactive Video Object Segmentation Using Reliability-Based Attention Maps},
author={Yuk Heo and Yeong Jun Koh and Chang-Su Kim},
booktitle={CVPR},
year={2021},
url={https://openaccess.thecvf.com/content/CVPR2021/papers/Heo_Guided_Interactive_Video_Object_Segmentation_Using_Reliability-Based_Attention_Maps_CVPR_2021_paper.pdf}
}