Git Product home page Git Product logo

edsc-pytorch's Introduction

EDSC-pytorch

Code for Multiple Video Frame Interpolation via Enhanced Deformable Separable Convolution [arXiv] .

Pre-trained models

Google Drive

Baidu Cloud : bdfu

Environment

We are good in the environment:

python 3.7

CUDA 10.1

Pytorch 1.0.0

opencv-python 4.2.0

numpy 1.18.1

cupy 6.0.0

Usage

We provide two versions of our model. The EDSC_s model was trained to generate the midpoint (in time) of the two input frames. And you can either choose the l1 or the lf model for distortion and perceptual quality, respectively.

We are good to run

python run.py --model EDSC_s --model_state EDSC_s_l1.ckpt --out out.png

The EDSC_m model is able to generate a frame at an arbirary time position. For instance, to generate an intermediate frame at t=0.1, we are good to run

python run.py --model EDSC_m --model_state EDSC_m.ckpt --time 0.1 --out out.png

Please see the paper for more details.

Citation

@article{EDSC,
    author={Cheng, Xianhang and Chen, Zhenzhong},
    journal={IEEE Transactions on Pattern Analysis and Machine Intelligence}, 
    title={Multiple Video Frame Interpolation via Enhanced Deformable Separable Convolution}, 
    year={2021},
    doi={10.1109/TPAMI.2021.3100714}
}

Acknowledgement

Part of the code was adapted from sepconv-slomo. A huge thanks to the authors!

edsc-pytorch's People

Contributors

xianhang avatar

Stargazers

 avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar

Watchers

 avatar  avatar  avatar  avatar  avatar  avatar  avatar

edsc-pytorch's Issues

Train code

Hi, is the train code available for this?
Thanks

Arbitrary-Position Frame Interpolation

hello,I want to know that when you train the model at any time, you first set a fixed time t, complete the complete training, and then achieve it through fine-tuning ?
Or there is no fixed time when practicing model, GT at different times are randomly sent to the network for learning?

training code

Could you provide us with training code? Thank you very much!

Requirements for running the code

Hi! Thanks for your contributions to frame interpolation! I will appreciate that you can provide the requirements for running your code correctly. Especially the version of pytorch and cuda. Thanks!

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.