Repository files navigation

This project is the implement ofReal-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 that4.22.lite is quite suitable for post-processing ofsome diffusion model generated videos.

2023.11 - We recently release newv4.7-4.10 optimized for anime scenes! We draw fromSAFA’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:

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 followPractical-RIFE, which aims to make RIFE more practical for users by adding various features and design new models with faster speed.

You may checkthis pull request for supporting macOS.

git clone git@github.com:megvii-research/ECCV2022-RIFE.gitcd ECCV2022-RIFEpip3 install -r requirements.txt

• Download the pretrainedHD models fromhere. (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 toevaluation.

Video Frame Interpolation

You can use ourdemo 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 forOptical Flow Estimation and refer to#291 forVideo 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

Place the pre-trained models intrain_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

DownloadRIFE model orRIFE_m model reported by our paper.

UCF101: DownloadUCF101 dataset at ./UCF101/ucf101_interp_ours/

Vimeo90K: DownloadVimeo90K dataset at ./vimeo_interp_test

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

HD: DownloadHD dataset at ./HD_dataset. We also provide agoogle drive download link.

# RIFEpython3 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_mpython3 benchmark/HD_multi_4X.py# "PSNR: 22.96(544*1280), 31.87(720p), 34.25(1080p)"

DownloadVimeo90K 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

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

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

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

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

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}}

Optical Flow:ARFlowpytorch-liteflownetRAFTpytorch-PWCNet

Video Interpolation:DVFTOflowSepConvDAINCAINMEMC-NetSoftSplatBMBCEDSCEQVI