(Image from https://drive.google.com/file/d/1i3xlKb7ax7Y70khcTcuePi6E7crO_dFc/view?usp=sharing)

Automatically downloads the onnx and prototxt files on the first run. It is necessary to be connected to the Internet while downloading.

For the sample images,

$ python3 rife.py

If you want to specify the input image, put the first image path after the --input option, and the next image path after the --input2 option.
You can use --savepath option to change the name of the output file to save.

$ python3 rife.py --input IMAGE_PATH1 --input2 IMAGE_PATH2 --savepath SAVE_IMAGE_PATH

The --input option can also specify the directory path where the images are located.

$ film rife.py --input DIR_PATH

By adding the --video option, you can input the video.
If you pass 0 as an argument to VIDEO_PATH, you can use the webcam input instead of the video file.

$ python3 rife.py --video VIDEO_PATH --savepath SAVE_VIDEO_PATH

for 4X interpolation.

$ python3 rife.py --exp 2

• ECCV2022-RIFE

Pytorch

ONNX opset=16

RIFE_HDv3.onnx.prototxt