Skip to content
master
Switch branches/tags
Code

Latest commit

 

Git stats

Files

Permalink
Failed to load latest commit information.
Type
Name
Latest commit message
Commit time
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

DTVNet — Official PyTorch Implementation

Python 3.7 PyTorch 1.5.1 License MIT

Official pytorch implementation of the paper "DTVNet: Dynamic Time-lapse Video Generation via Single Still Image, ECCV'20 (Spotlight)". The arxiv version will be released after filing the patent.

For any inquiries, please contact Jiangning Zhang at 186368@zju.edu.cn

Demo

Demo

Using the Code

Requirements

This code has been developed under Python3.7, PyTorch 1.5.1 and CUDA 10.1 on Ubuntu 16.04.

# Install python3 packages
pip3 install -r requirements.txt

Datasets in the paper

Unsupervised Flow Estimation

  1. Our another work ARFlow (CVPR'20) is used as the unsupervised optical flow estimator in the paper. You can refer to flow/ARFlow/README.md for more details.

  2. Training:

    > Modify `configs/sky.json` if you use another data_root or settings.
    cd flow/ARFlow
    python3 train.py
  3. Testing:

    > Pre-traind model is located in `checkpoints/Sky/sky_ckpt.pth.tar`
    python3 inference.py --show  # Test and show a single pair images.
    python3 inference.py --root ../../data/sky_timelapse/ --save_path ../../data/sky_timelapse/flow/  # Generate optical flow in advance for Sky Time-lapse dataset.

Running

  1. Train DTVNet model.

    > Modify `configs/sky_timelapse.json` if you use another data_root or settings.
    python3 train.py
  2. Test DTVNet model.

    > Pre-traind model is located in `checkpoints/DTV_Sky/200708162546`
    > Results are save in `checkpoints/DTV_Sky/200708162546/results`
    python3 Test.py

Citation

If our work is useful for your research, please consider citing:

@inproceedings{zhang2020dtvnet,
  title={Dtvnet: Dynamic time-lapse video generation via single still image},
  author={Zhang, Jiangning and Xu, Chao and Liu, Liang and Wang, Mengmeng and Wu, Xia and Liu, Yong and Jiang, Yunliang},
  booktitle={European Conference on Computer Vision},
  pages={300--315},
  year={2020},
  organization={Springer}
}

About

DTVNet: Dynamic Time-lapse Video Generation via Single Still Image, ECCV'20 Spotlight.

Resources

Releases

No releases published

Packages

No packages published