DAIN (Depth-Aware Video Frame Interpolation)

Project | Paper

Wenbo Bao, Wei-Sheng Lai, Chao Ma, Xiaoyun Zhang, Zhiyong Gao, and Ming-Hsuan Yang

IEEE Conference on Computer Vision and Pattern Recognition, Long Beach, CVPR 2019

This work is developed based on our TPAMI work MEMC-Net, where we propose the adaptive warping layer. Please also consider referring to it.

Table of Contents

  1. Introduction
  2. Citation
  3. Requirements and Dependencies
  4. Installation
  5. Testing Pre-trained Models
  6. Downloading Results
  7. Slow-motion Generation
  8. Training New Models
  9. Google Colab Demo

Introduction

We propose the Depth-Aware video frame INterpolation (DAIN) model to explicitly detect the occlusion by exploring the depth cue. We develop a depth-aware flow projection layer to synthesize intermediate flows that preferably sample closer objects than farther ones. Our method achieves state-of-the-art performance on the Middlebury dataset. We provide videos here.

Citation

If you find the code and datasets useful in your research, please cite:

@inproceedings{DAIN,
    author    = {Bao, Wenbo and Lai, Wei-Sheng and Ma, Chao and Zhang, Xiaoyun and Gao, Zhiyong and Yang, Ming-Hsuan}, 
    title     = {Depth-Aware Video Frame Interpolation}, 
    booktitle = {IEEE Conference on Computer Vision and Pattern Recognition},
    year      = {2019}
}
@article{MEMC-Net,
     title={MEMC-Net: Motion Estimation and Motion Compensation Driven Neural Network for Video Interpolation and Enhancement},
     author={Bao, Wenbo and Lai, Wei-Sheng, and Zhang, Xiaoyun and Gao, Zhiyong and Yang, Ming-Hsuan},
     journal={IEEE Transactions on Pattern Analysis and Machine Intelligence},
     doi={10.1109/TPAMI.2019.2941941},
     year={2018}
}

Requirements and Dependencies

Installation

Download repository:

$ git clone https://github.com/baowenbo/DAIN.git

Before building Pytorch extensions, be sure you have pytorch >= 1.0.0:

$ python -c "import torch; print(torch.__version__)"

Generate our PyTorch extensions:

$ cd DAIN
$ cd my_package 
$ ./build.sh

Generate the Correlation package required by PWCNet:

$ cd ../PWCNet/correlation_package_pytorch1_0
$ ./build.sh

Testing Pre-trained Models

Make model weights dir and Middlebury dataset dir:

$ cd DAIN
$ mkdir model_weights
$ mkdir MiddleBurySet

Download pretrained models,

$ cd model_weights
$ wget http://vllab1.ucmerced.edu/~wenbobao/DAIN/best.pth

and Middlebury dataset:

$ cd ../MiddleBurySet
$ wget http://vision.middlebury.edu/flow/data/comp/zip/other-color-allframes.zip
$ unzip other-color-allframes.zip
$ wget http://vision.middlebury.edu/flow/data/comp/zip/other-gt-interp.zip
$ unzip other-gt-interp.zip
$ cd ..

preinstallations:

$ cd PWCNet/correlation_package_pytorch1_0
$ sh build.sh
$ cd ../my_package
$ sh build.sh
$ cd ..

We are good to go by:

$ CUDA_VISIBLE_DEVICES=0 python demo_MiddleBury.py

The interpolated results are under MiddleBurySet/other-result-author/[random number]/, where the random number is used to distinguish different runnings.

Downloading Results

Our DAIN model achieves the state-of-the-art performance on the UCF101, Vimeo90K, and Middlebury (eval and other). Download our interpolated results with:

$ wget http://vllab1.ucmerced.edu/~wenbobao/DAIN/UCF101_DAIN.zip
$ wget http://vllab1.ucmerced.edu/~wenbobao/DAIN/Vimeo90K_interp_DAIN.zip
$ wget http://vllab1.ucmerced.edu/~wenbobao/DAIN/Middlebury_eval_DAIN.zip
$ wget http://vllab1.ucmerced.edu/~wenbobao/DAIN/Middlebury_other_DAIN.zip

Slow-motion Generation

Our model is fully capable of generating slow-motion effect with minor modification on the network architecture. Run the following code by specifying time_step = 0.25 to generate x4 slow-motion effect:

$ CUDA_VISIBLE_DEVICES=0 python demo_MiddleBury_slowmotion.py --netName DAIN_slowmotion --time_step 0.25

or set time_step to 0.125 or 0.1 as follows

$ CUDA_VISIBLE_DEVICES=0 python demo_MiddleBury_slowmotion.py --netName DAIN_slowmotion --time_step 0.125
$ CUDA_VISIBLE_DEVICES=0 python demo_MiddleBury_slowmotion.py --netName DAIN_slowmotion --time_step 0.1

to generate x8 and x10 slow-motion respectively. Or if you would like to have x100 slow-motion for a little fun.

$ CUDA_VISIBLE_DEVICES=0 python demo_MiddleBury_slowmotion.py --netName DAIN_slowmotion --time_step 0.01

You may also want to create gif animations by:

$ cd MiddleBurySet/other-result-author/[random number]/Beanbags
$ convert -delay 1 *.png -loop 0 Beanbags.gif //1*10ms delay 

Have fun and enjoy yourself!

Training New Models

Download the Vimeo90K triplet dataset for video frame interpolation task, also see here by Xue et al., IJCV19.

$ cd DAIN
$ mkdir /path/to/your/dataset & cd /path/to/your/dataset 
$ wget http://data.csail.mit.edu/tofu/dataset/vimeo_triplet.zip
$ unzip vimeo_triplet.zip
$ rm vimeo_triplet.zip

Download the pretrained MegaDepth and PWCNet models

$ cd MegaDepth/checkpoints/test_local
$ wget http://vllab1.ucmerced.edu/~wenbobao/DAIN/best_generalization_net_G.pth
$ cd ../../../PWCNet
$ wget http://vllab1.ucmerced.edu/~wenbobao/DAIN/pwc_net.pth.tar
$ cd  ..

Run the training script:

$ CUDA_VISIBLE_DEVICES=0 python train.py --datasetPath /path/to/your/dataset --batch_size 1 --save_which 1 --lr 0.0005 --rectify_lr 0.0005 --flow_lr_coe 0.01 --occ_lr_coe 0.0 --filter_lr_coe 1.0 --ctx_lr_coe 1.0 --alpha 0.0 1.0 --patience 4 --factor 0.2

The optimized models will be saved to the model_weights/[random number] directory, where [random number] is generated for different runs.

Replace the pre-trained model_weights/best.pth model with the newly trained model_weights/[random number]/best.pth model. Then test the new model by executing:

$ CUDA_VISIBLE_DEVICES=0 python demo_MiddleBury.py

Google Colab Demo

This is a modification of DAIN that allows the usage of Google Colab and is able to do a full demo interpolation from a source video to a target video.

Original Notebook File by btahir can be found here.

To use the Colab, follow these steps:

Colab file authors: Styler00Dollar and Alpha.

Contact

Wenbo Bao; Wei-Sheng (Jason) Lai

License

See MIT License