/Copy-and-Paste-Networks-for-Deep-Video-Inpainting

Official Pytorch implementation of Copy-and-Paste Networks for Deep Video Inpainting (ICCV 2019)

Primary LanguagePython

Copy-and-Paste Networks for Deep Video Inpainting (ICCV 2019)

Official pytorch implementation for "Copy-and-Paste Networks for Deep Video Inpainting" (ICCV 2019) V.1.0

[Paper] [Supp]

Video result

IMAGE ALT TEXT HERE

Requirements

  • python 3.6
  • pytorch 0.4

Download weights

mkdir ./weight
wget -O ./weight/weight.pth "https://www.dropbox.com/s/vbh12ay2ubrw3m9/weight.pth?dl=0"

Run

python CPNet_test.py -g [gpu_num] -D [dataset_path]

Reference

If you use this code please cite:

@InProceedings{lee2019cpnet,
author = {Lee, Sungho and Oh, Seoung Wug and Won, DaeYeun and Kim, Seon Joo},
title = {Copy-and-Paste Networks for Deep Video Inpainting},
booktitle = {International Conference on Computer Vision (ICCV)},
year = {2019}
}

Related works

Please check out our another approach for video inpainting.

Onion-Peel Networks for Deep Video Completion
Seoung Wug Oh, Sungho Lee, Joon-Young Lee, Seon Joo Kim
ICCV 2019

[Paper] [Github] [Video]

Term of use

This software is for non-commercial use only. The source code is released under the Attribution-NonCommercial-ShareAlike (CC BY-NC-SA) Licence (see this for details)