2018-01-13 23:32 GMT-02:00 Michael Niedermayer <mich...@niedermayer.cc>:
> On Fri, Jan 12, 2018 at 11:56:07AM -0200, Pedro Arthur wrote: > > 2018-01-12 0:06 GMT-02:00 Michael Niedermayer <mich...@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. > > Iam sure our users would want to train the filter in some cases. > use cases for different types of content anime vs movies with actors for > example likely benefit from seperate training sets. > > The training code could be seperate from the filter > > Also another issue is the space requirements that result out of the > training. > This was an issue with NNEDI previously IIRC > > > > > > There are also method which does not use NN like A+ [5] and ANR. > > How do these perform in relation to the latest NN based solutions ? > Comparing psnr the first NN method (SRCNN) achieves the same quality but evaluation is faster than A+, or better quality at same speed. Newer NN methods ([3], [4]) uses "perceptual loss" functions which degrades the psnr but the images are much more sharp and appear to have better quality than those that maximize psnr. > Also i think its a great project, you should definitly mentor this if it > interrests you > > > > > > [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 > > _______________________________________________ > > ffmpeg-devel mailing list > > ffmpeg-devel@ffmpeg.org > > http://ffmpeg.org/mailman/listinfo/ffmpeg-devel > > -- > Michael GnuPG fingerprint: 9FF2128B147EF6730BADF133611EC787040B0FAB > > Awnsering whenever a program halts or runs forever is > On a turing machine, in general impossible (turings halting problem). > On any real computer, always possible as a real computer has a finite > number > of states N, and will either halt in less than N cycles or never halt. > > _______________________________________________ > ffmpeg-devel mailing list > ffmpeg-devel@ffmpeg.org > http://ffmpeg.org/mailman/listinfo/ffmpeg-devel > > _______________________________________________ ffmpeg-devel mailing list ffmpeg-devel@ffmpeg.org http://ffmpeg.org/mailman/listinfo/ffmpeg-devel
