Skip to content

LeHanhcs/SDPF_VideoResequencing

Repository files navigation

Regenerating Arbitrary Video Sequences with Distillation Path-Finding

by Thi-Ngoc-Hanh Le, Sheng-Yi Yao, Chun-Te Wu and Tong-Yee Lee.
Computer Graphics Group at National Cheng-Kung University, Taiwan.
Training code will be updated.

This resposity is the official implementation of our video resequencing system. This paper has been accepted for publication on IEEE Transactions on Visualization and Computer Graphics (Jan/2023).

Paper

  • Published online on IEEE Transactions on Visualization and Computer Graphics, link
  • Project website: link
  • Demo video: youtube link
  • Paper *.pdf

Introduction

If the video has long been mentioned as a widespread visualization form, the animation sequence in the video is mentioned as storytelling for people. Producing an animation requires intensive human labor from skilled professional artists to obtain plausible animation in both content and motion direction, incredibly for animations with complex content, multiple moving objects, and dense movement. We first learn the feature correlation on the frameset of the given video through a proposed network called RSFNet. Then, we develop a novel path-finding algorithm, SDPF, which formulates the knowledge of motion directions of the source video to estimate the smooth and plausible sequences.

framework

Requirements

tensorflow==1.15
tensorflow-estimator==1.15.1
keras==2.3.1
matplotlib
scikit-image
pandas
tqdm
opencv
scikit-learn
conda-forge::imageio-ffmpeg

Guidance of data/code usage

python simulate.py –m 1 –s 0

-n: model name, in the paper is Tri_Fuse_AE
-s: user-specified initial frame (starting frame), 0 represents the 0th frame in the input video (or a bunch of pictures)

Acknowledgments

Thanks for the authors of PWC-Net: CNNs for Optical Flow Using Pyramid, Warping, and Cost Volume for the code of generating optical flow.
We inherit the code from their responsitory for optical flow production in our system.

Citation

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

@ARTICLE{10018537,
  author={Le, Thi-Ngoc-Hanh and Yao, Sheng-Yi and Wu, Chun-Te and Lee, Tong-Yee},
  journal={IEEE Transactions on Visualization and Computer Graphics}, 
  title={Regenerating Arbitrary Video Sequences with Distillation Path-Finding}, 
  year={2023},
  volume={},
  number={},
  pages={1-14},
  keywords={Animation;Feature extraction;Correlation;Shape;Video sequences;Prediction algorithms;Measurement;animation;sequencing;RSFNet;distillation;SDPF},
  doi={10.1109/TVCG.2023.3237739}}
}

Contact

If you have any question, please email me: ngochanh.le1987@gmail.com or tonylee@mail.ncku.edu.tw (corresponding author)

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages