Need help with Music-Dance-Video-Synthesis?
Click the “chat” button below for chat support from the developer who created it, or find similar developers for support.

About the developer

xrenaa
179 Stars 20 Forks 52 Commits 5 Opened issues

Description

(ACM MM 20 Oral) PyTorch implementation of Self-supervised Dance Video Synthesis Conditioned on Music

Services available

!
?

Need anything else?

Contributors list

Self-supervised Dance Video Synthesis Conditioned on Music

Pytorch implementation for this paper by Xuanchi Ren, Haoran Li, Zijian Huang, Qifeng Chen

To appear in ACM MM 2020

[Paper] [Paper_MM]

The demo video is shown at: https://youtu.be/UNHv7uOUExU

The dataset and the code for training and test is released.

A notebook for demo and quick start will be provided soon.

Some Demo:

More samples can be seen in demo video.

Requirement:

python 3.5 + pytorch 1.0

For the Testing part, you should install ffmpeg for music video.

We use tensorboardX for logging. If you don't install it, you can just comment the line in train.py.

Training:

This training process is intended for the clean part dataset, which could be downloaded here. 1. Download the dataset and put it under ./dataset

  1. Run
    python
    python train.py
    
    training script will load config of config.py. If you want to train the model on other datasets, you should change the config in config.py.

Testing:

If you want to use the pretrained model, you can firstly download it from here, put it under "pretrainmodel" and change the path of getdemo.py to "./pretrainmodel/generator0400.pth". 1. Run

python get_demo.py --output the_output_path
2. Make the output skeleton sequence to music video
cd Demo
./frame2vid.sh
Note that you should change the paths and the "max" variable in frame2vid.sh.

Pose2Vid:

For this part, we adapt the method of the paper "Everybody dance now".

And We use this pytorch implementation.

Metrics:

For the proposed cross-modal metric in our paper, we re-implement the paper: Human Motion Analysis with Deep Metric Learning (ECCV 2018).

The implementation of this paper can be seen at: https://github.com/xrenaa/Human-Motion-Analysis-with-Deep-Metric-Learning

Dataset:

To use the dataset, please refer the notebook "dataset/usage_dataset.ipynb"

As state in the paper, we collect 60 videos in total, and divide them into 2 part according to the cleaness of the skeletons.

The clean part(40 videos): https://drive.google.com/file/d/1o79F2F7-dZ7Cvpzf6hsVMwvfNg9LM3_K/view?usp=sharing

The noisy part(20 videos): https://drive.google.com/file/d/1pZ3JszX7393dQwm6x6bxxbiKb0wLIJGE/view?usp=sharing

To support further study, we also provide other collected data:

Ballet: https://drive.google.com/open?id=1NR6S20EI1C37fsDhaNkRI_P1MLT9Ox7u

Popping: https://drive.google.com/file/d/1oLIxtczDZBvPdCAk8wuiI9b4FsnCItMG/view?usp=sharing

Boy_kpop: https://drive.google.com/file/d/14-kEdudvaGLSapAr4prp4D67wzyACVQt/view?usp=sharing

Besides, we also provide the BaiduNetDisk version: https://pan.baidu.com/s/15wLkdPnlZiCxgnPv51hgpg (includes all the dataset)

Questions

If you have questions for our work, please email to [email protected]

Citation

If you use this code for your research, please cite our paper.

@InProceedings{ren_mm_dance,
author = {Xuanchi Ren, Haoran Li, Zijian Huang, Qifeng Chen},
title = {Self-supervised Dance Video Synthesis Conditioned on Music},
booktitle = {ACM MM},
year = {2020}
}

We use cookies. If you continue to browse the site, you agree to the use of cookies. For more information on our use of cookies please see our Privacy Policy.