[FFmpeg-devel] GSoC 2018

Pedro Arthur bygrandao at gmail.com
Fri Jan 12 15:56:07 EET 2018


2018-01-12 0:06 GMT-02:00 Michael Niedermayer <michael at niedermayer.cc>:

> if pedro is up to date on this stuff, then maybe he wants to mentor this
>
> either way, links to relevant research, tests, literature are welcome
>
> I can mentor this.

One of the first NN based method was [1] which has a very simple network
layout, only 3 convolution layers. More complex methods can be found in
[2], [3], [4].
The important question is where we are going to perfom only inference,
using a pre-trained net or we will also train the net. The first is more
easy to do but we don't exploit the content knowledge we have, the second
is more powerful as it adapts to the content but requires training which
may be  expensive, in this case it would be best to use some library to
perform the training.

There are also method which does not use NN like A+ [5] and ANR.

[1] - https://arxiv.org/abs/1501.00092
[2] - https://arxiv.org/abs/1609.05158
[3] - https://arxiv.org/abs/1603.08155
[4] - https://arxiv.org/abs/1609.04802
[5] -
http://www.vision.ee.ethz.ch/~timofter/publications/Timofte-ACCV-2014.pdf


More information about the ffmpeg-devel mailing list