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

About the developer

147 Stars 13 Forks MIT License 41 Commits 2 Opened issues


A state-of-the-art Video Frame Interpolation Method using feature flows blending. (CVPR 2020)

Services available


Need anything else?

Contributors list


Paper | Supp

A state-of-the-art Video Frame Interpolation Method using deep semantic flows blending.

FeatureFlow: Robust Video Interpolation via Structure-to-texture Generation (IEEE Conference on Computer Vision and Pattern Recognition 2020)

To Do List

  • [x] Preprint
  • [x] Training code

Table of Contents

  1. Requirements
  2. Demos
  3. Installation
  4. Pre-trained Model
  5. Download Results
  6. Evaluation
  7. Test your video
  8. Training
  9. Citation


  • Ubuntu
  • PyTorch (>=1.1)
  • Cuda (>=10.0) & Cudnn (>=7.0)
  • mmdet 1.0rc (from
  • visdom (not necessary)


is provided, but do not use it directly. It is just for reference because it contains another project's dependencies.

Video demos

Click the picture to Download one of them or click Here(Google) or Here(Baidu)(key: oav2) to download 360p demos.

360p demos(including comparisons):

720p demos:


  • clone this repo
  • git clone
  • install mmdetection: please follow the guidence in its github
    $ cd mmdetection
    $ pip install -r requirements/build.txt
    $ pip install "git+"
    $ pip install -v -e .  # or "python develop"
    $ pip list | grep mmdet
  • Download test set
    $ unzip
    $ cd vimeo_interp_test
    $ mkdir sequences
    $ cp target/* sequences/ -r
    $ cp input/* sequences/ -r
  • Download BDCN's pre-trained model:bdcnpretrainedon_bsds500.pth to ./model/bdcn/final-model/

Ps: For your convenience, you can only download the bdcnpretrainedon_bsds500.pth: Google Drive or all of the pre-trained bdcn models its authors provided: Google Drive. For a Baidu Cloud link, you can resort to BDCN's GitHub repository.

$ pip install scikit-image visdom tqdm prefetch-generator

Pre-trained Model

Google Drive

Baidu Cloud: ae4x

Place FeFlow.ckpt to ./checkpoints/.

Download Results

Google Drive

Baidu Cloud: pc0k


$ CUDA_VISIBLE_DEVICES=0 python --checkpoint ./checkpoints/FeFlow.ckpt --dataset_root ~/datasets/videos/vimeo_interp_test --visdom_env test --vimeo90k --imgpath ./results/

Test your video

$ CUDA_VISIBLE_DEVICES=0 python --checkpoint checkpoints/FeFlow.ckpt --video_path ./yourvideo.mp4 --t_interp 4 --slow_motion

sets frame multiples, only power of 2(2,4,8...) are supported. Use flag
to slow down the video which maintains the original fps.

The output video will be saved as output.mp4 in your working diractory.


Training Code is available now. I can't run it for comfirmation now because I've left the Lab, but I'm sure it will work with right argument settings.

  • Please read the arguments' help carefully to fully control the two-step training.
  • Pay attention to the
    which is the flag to set the model to Stage-I or Stage-II.
  • 2 GPUs is necessary for training or the small batch_size will cause training process crash.
  • Deformable CNN is not stable enough so that you may face training crash sometimes(I didn't fix the random seed), but it can be detected soon after the beginning of running by visualizing results using Visdom.
  • Visdom visualization codes[line 75, 201-216 and 338-353] are included which is good for viewing training process and checking crash.


author = {Gui, Shurui and Wang, Chaoyue and Chen, Qihua and Tao, Dacheng},
title = {FeatureFlow: Robust Video Interpolation via Structure-to-Texture Generation},
booktitle = {The IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2020}


Shurui Gui; Chaoyue Wang


See MIT License

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.