[FFmpeg-devel] [FFmpeg-cvslog] Adds ESPCN super resolution filter merged with SRCNN filter.

[Daniel Oberhoff]

If I may pitch in: why not separate issues? I could imagine a generic convolutional nn filter which gets given topology and weights via some config file. Then provide files separately for this particular trained network.

Gruß!

Daniel Oberhoff

> Am 03.07.2018 um 14:11 schrieb Gyan Doshi <gyandoshi at gmail.com>:
> 
> 
>> On 03-07-2018 12:49 AM, Jean-Baptiste Kempf wrote:
>> On Mon, 2 Jul 2018, at 20:52, Pedro Arthur wrote:
> 
>>>> This code is not open source, and is not compatible with LGPLv2.1:
>>>> 
>>>> "If you use/adapt our code in your work (either as a stand-alone tool or as a component of any algorithm),
>>>> you need to appropriately cite our ECCV 2014 paper or arXiv paper."
>>>> 
>>>> Reimplementation of the code in a different language does not remove IP.
>>> The paper is properly cited in libavfilter/vf_sr.c.
>>> 
>>> I not specialist in  IP rights but  there is nothing novel in the code
>>> (TBH there is no code at all, look at srcnn.m) it is just plain
>>> convolution, basic math machinery, we are just applying a bunch of
>>> filter convolution to an image.
>> Well, either it is based on a paper and the matlab code, or it is not.
>> If it is, it's a big issue, since this is not open source compatible.
>> If it is just convolution, then why is it based on this paper?
>> What is the source of those numbers?
>>> If you're referring to using his trained data, Ok, we could train our
>>> own weights if it is really an issue.
>> Sorry, but you need to be able to give the source of your code. Aka the original source that can create the code.
> 
> I was planning to document this filter this coming weekend, but if there's serious doubt over its inclusion, I'll wait.
> 
> Gyan
> _______________________________________________
> ffmpeg-devel mailing list
> ffmpeg-devel at ffmpeg.org
> http://ffmpeg.org/mailman/listinfo/ffmpeg-devel