FFmpeg 4.3.8
Since* 4.2
#

Remove the rain in the input image/video by applying the derain methods based on convolutional neural networks. Supported models:

Training as well as model generation scripts are provided in the repository at https://github.com/XueweiMeng/derain_filter.git.

Native model files (.model) can be generated from TensorFlow model files (.pb) by using tools/python/convert.py

The filter accepts the following options:

filter_type

Specify which filter to use. This option accepts the following values:

derain

Derain filter. To conduct derain filter, you need to use a derain model.

dehaze

Dehaze filter. To conduct dehaze filter, you need to use a dehaze model.

Default value is derain.

dnn_backend

Specify which DNN backend to use for model loading and execution. This option accepts the following values:

native

Native implementation of DNN loading and execution.

tensorflow

TensorFlow backend. To enable this backend you need to install the TensorFlow for C library (see https://www.tensorflow.org/install/install_c) and configure FFmpeg with --enable-libtensorflow

Default value is native.

model

Set path to model file specifying network architecture and its parameters. Note that different backends use different file formats. TensorFlow and native backend can load files for only its format.

It can also be finished with dnn_processing filter.