[FFmpeg-devel] Documentation for sr filter

Submitted by Sergey Lavrushkin on Aug. 9, 2018, 5:16 p.m.

Details

Message ID CAAeE=qpaKiYKxE7vqukwfF7AKzv8Kw+ukk-7kE2if78bDpvXBw@mail.gmail.com
State New
Headers show

Commit Message

Sergey Lavrushkin Aug. 9, 2018, 5:16 p.m.
2018-08-07 13:14 GMT+03:00 Moritz Barsnick <barsnick@gmx.net>:

> On Tue, Aug 07, 2018 at 00:24:29 +0300, Sergey Lavrushkin wrote:
> > +@table @option
> > +@item model
> > +Specify what super-resolution model to use. This option accepts the
> following values:
>            ^ nit: which
>
> > +Specify what DNN backend to use for model loading and execution. This
> option accepts
> Ditto
>
> > +Allowed values are @code{2}, @code{3} and @code{4}. Scale factor is
> neccessary
>                                                                        ^
> necessary
>
> > +Note that different backends use different file format. If path to model
>                                                    ^ formats
>

Here is updated patch.

Patch hide | download patch | download mbox

From 1fed1ea07a5727d937228307bffbde13e6727669 Mon Sep 17 00:00:00 2001
From: Sergey Lavrushkin <dualfal@gmail.com>
Date: Fri, 3 Aug 2018 17:24:00 +0300
Subject: [PATCH 9/9] doc/filters.texi: Adds documentation for sr filter.

---
 doc/filters.texi | 60 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 60 insertions(+)

diff --git a/doc/filters.texi b/doc/filters.texi
index 0b0903e5a7..e2436a24e7 100644
--- a/doc/filters.texi
+++ b/doc/filters.texi
@@ -15394,6 +15394,66 @@  option may cause flicker since the B-Frames have often larger QP. Default is
 @code{0} (not enabled).
 @end table
 
+@section sr
+
+Scale the input by applying one of the super-resolution methods based on
+convolutional neural networks.
+
+Training scripts as well as scripts for model generation are provided in
+the repository @url{https://github.com/HighVoltageRocknRoll/sr.git}.
+
+The filter accepts the following options:
+
+@table @option
+@item model
+Specify what super-resolution model to use. This option accepts the following values:
+
+@table @samp
+@item srcnn
+Super-Resolution Convolutional Neural Network model
+@url{https://arxiv.org/abs/1501.00092}.
+
+@item espcn
+Efficient Sub-Pixel Convolutional Neural Network model
+@url{https://arxiv.org/abs/1609.05158}.
+
+@end table
+
+Default value is @samp{srcnn}.
+
+@item dnn_backend
+Specify what DNN backend to use for model loading and execution. This option accepts
+the following values:
+
+@table @samp
+@item native
+Native implementation of DNN loading and execution.
+
+@item tensorflow
+TensorFlow backend @url{https://www.tensorflow.org/}. To enable this backend you
+need to install the TensorFlow for C library (see
+@url{https://www.tensorflow.org/install/install_c}) and configure FFmpeg with
+@code{--enable-libtensorflow}
+
+@end table
+
+Default value is @samp{native}.
+
+@item scale_factor
+Set scale factor for SRCNN model, for which custom model file was provided.
+Allowed values are @code{2}, @code{3} and @code{4}. Scale factor is neccessary
+for SRCNN model, because it accepts input upscaled using bicubic upscaling with
+proper scale factor.
+
+Default value is @code{2}.
+
+@item model_filename
+Set path to model file specifying network architecture and its parameters.
+Note that different backends use different file format. If path to model
+file is not specified, built-in models for 2x upscaling are used.
+
+@end table
+
 @anchor{subtitles}
 @section subtitles
 
-- 
2.14.1