hzwer/ECCV2022-RIFE

Real-Time Intermediate Flow Estimation for Video Frame Interpolation

YouTube | BiliBili | Colab | Tutorial | DeepWiki

Introduction

This project is the implement of Real-Time Intermediate Flow Estimation for Video Frame Interpolation. Currently, our model can run 30+FPS for 2X 720p interpolation on a 2080Ti GPU. It supports arbitrary-timestep interpolation between a pair of images.

2024.08 - We find that 4.22.lite is quite suitable for post-processing of some diffusion model generated videos.

2023.11 - We recently release new v4.7-4.10 optimized for anime scenes! We draw from SAFA’s research.

2022.7.4 - Our paper is accepted by ECCV2022. Thanks to all relevant authors, contributors and users!

From 2020 to 2022, we submitted RIFE for five submissions（rejected by CVPR21 ICCV21 AAAI22 CVPR22). Thanks to all anonymous reviewers, your suggestions have helped to significantly improve the paper!

ECCV Poster | ECCV 5-min presentation | 论文中文介绍 | rebuttal (2WA1WR->3WA)

Pinned Software: RIFE-App | FlowFrames | SVFI (中文)

16X interpolation results from two input images:

Software

Flowframes | SVFI(中文) | Waifu2x-Extension-GUI | Autodesk Flame | SVP | mpv_PlayKit | enhancr

RIFE-App(Paid) | Steam-VFI(Paid)

We are not responsible for and participating in the development of above software. According to the open source license, we respect the commercial behavior of other developers.

VapourSynth-RIFE | RIFE-ncnn-vulkan | VapourSynth-RIFE-ncnn-Vulkan | vs-mlrt

If you are a developer, welcome to follow Practical-RIFE, which aims to make RIFE more practical for users by adding various features and design new models with faster speed.

You may check this pull request for supporting macOS.

CLI Usage

Installation

git clone [email protected]:megvii-research/ECCV2022-RIFE.git
cd ECCV2022-RIFE
pip3 install -r requirements.txt

• Download the pretrained HD models from here. (百度网盘链接:https://pan.baidu.com/share/init?surl=u6Q7-i4Hu4Vx9_5BJibPPA 密码:hfk3，把压缩包解开后放在 train_log/*)

• Unzip and move the pretrained parameters to train_log/*

• This model is not reported by our paper, for our paper model please refer to evaluation.

Run

Video Frame Interpolation

You can use our demo video or your own video.

python3 inference_video.py --exp=1 --video=video.mp4 

(generate video_2X_xxfps.mp4)

python3 inference_video.py --exp=2 --video=video.mp4

(for 4X interpolation)

python3 inference_video.py --exp=1 --video=video.mp4 --scale=0.5

(If your video has very high resolution such as 4K, we recommend set --scale=0.5 (default 1.0). If you generate disordered pattern on your videos, try set --scale=2.0. This parameter control the process resolution for optical flow model.)

python3 inference_video.py --exp=2 --img=input/

(to read video from pngs, like input/0.png ... input/612.png, ensure that the png names are numbers)

python3 inference_video.py --exp=2 --video=video.mp4 --fps=60

(add slomo effect, the audio will be removed)

python3 inference_video.py --video=video.mp4 --montage --png

(if you want to montage the origin video and save the png format output)

Extended Application

You may refer to #278 for Optical Flow Estimation and refer to #291 for Video Stitching.

Image Interpolation

python3 inference_img.py --img img0.png img1.png --exp=4

(2^4=16X interpolation results) After that, you can use pngs to generate mp4:

ffmpeg -r 10 -f image2 -i output/img%d.png -s 448x256 -c:v libx264 -pix_fmt yuv420p output/slomo.mp4 -q:v 0 -q:a 0

You can also use pngs to generate gif:

ffmpeg -r 10 -f image2 -i output/img%d.png -s 448x256 -vf "split[s0][s1];[s0]palettegen=stats_mode=single[p];[s1][p]paletteuse=new=1" output/slomo.gif

Run in docker

Place the pre-trained models in train_log/\*.pkl (as above)

Building the container:

docker build -t rife -f docker/Dockerfile .

Running the container:

docker run --rm -it -v $PWD:/host rife:latest inference_video --exp=1 --video=untitled.mp4 --output=untitled_rife.mp4

docker run --rm -it -v $PWD:/host rife:latest inference_img --img img0.png img1.png --exp=4

Using gpu acceleration (requires proper gpu drivers for docker):

docker run --rm -it --gpus all -v /dev/dri:/dev/dri -v $PWD:/host rife:latest inference_video --exp=1 --video=untitled.mp4 --output=untitled_rife.mp4

Evaluation

Download RIFE model or RIFE_m model reported by our paper.

UCF101: Download UCF101 dataset at ./UCF101/ucf101_interp_ours/

Vimeo90K: Download Vimeo90K dataset at ./vimeo_interp_test

MiddleBury: Download MiddleBury OTHER dataset at ./other-data and ./other-gt-interp

HD: Download HD dataset at ./HD_dataset. We also provide a google drive download link.

# RIFE
python3 benchmark/UCF101.py
# "PSNR: 35.282 SSIM: 0.9688"
python3 benchmark/Vimeo90K.py
# "PSNR: 35.615 SSIM: 0.9779"
python3 benchmark/MiddleBury_Other.py
# "IE: 1.956"
python3 benchmark/HD.py
# "PSNR: 32.14"

# RIFE_m
python3 benchmark/HD_multi_4X.py
# "PSNR: 22.96(544*1280), 31.87(720p), 34.25(1080p)"

Training and Reproduction

Download Vimeo90K dataset.

We use 16 CPUs, 4 GPUs and 20G memory for training:

python3 -m torch.distributed.launch --nproc_per_node=4 train.py --world_size=4

Revision History

2021.3.18 arXiv: Modify the main experimental data, especially the runtime related issues.

2021.8.12 arXiv: Remove pre-trained model dependency and propose privileged distillation scheme for frame interpolation. Remove census loss supervision.

2021.11.17 arXiv: Support arbitrary-time frame interpolation, aka RIFEm and add more experiments.

Recommend

We sincerely recommend some related papers:

CVPR22 - Optimizing Video Prediction via Video Frame Interpolation

CVPR22 - Video Frame Interpolation with Transformer

CVPR22 - IFRNet: Intermediate Feature Refine Network for Efficient Frame Interpolation

CVPR23 - A Dynamic Multi-Scale Voxel Flow Network for Video Prediction

CVPR23 - Extracting Motion and Appearance via Inter-Frame Attention for Efficient Video Frame Interpolation

Citation

If you think this project is helpful, please feel free to leave a star or cite our paper:

@inproceedings{huang2022rife,
  title={Real-Time Intermediate Flow Estimation for Video Frame Interpolation},
  author={Huang, Zhewei and Zhang, Tianyuan and Heng, Wen and Shi, Boxin and Zhou, Shuchang},
  booktitle={Proceedings of the European Conference on Computer Vision (ECCV)},
  year={2022}
}

Reference

Optical Flow: ARFlow pytorch-liteflownet RAFT pytorch-PWCNet

Video Interpolation: DVF TOflow SepConv DAIN CAIN MEMC-Net SoftSplat BMBC EDSC EQVI