[FFmpeg-devel] hardware aided video decoding

[Attila Kinali]

On Fri, 6 Jul 2007 16:00:30 +0300
Kostya <kostya.shishkov at gmail.com> wrote:

> And the real difference is in the first step. IIRC, there is something
> about using this as intermediate format in FFmpeg TODO and there was a
> patch to losslessly transcode from MSMPEG-4 (old DivX) to MPEG-4 (XviD).
> So it is ideal to put this common decoding part to the dedicated decoder.

I thought about doing such an intermediate format, but that might
be a little too much work for the beginning.
  
> And now to wavelets.
> I think it's easy to do on video card but will eat a lot of memory.
> The principle is the next: read data from one memory location, process and
> store at another place in video memory (may I say the word 'shaders'?).

My current idea how to implement MC looks very much like
a shader, thus it wouldnt be that wrong to talk about video shaders :)

> Inplace transform will be slower and less effective.
> Also while DCT is standard (almost), wavelet operations may differ
> (see Snow for example).

That's one of the issues with wavelets.
  

				Attila Kinali
-- 
Linux ist... wenn man einfache Dinge auch mit einer kryptischen
post-fix Sprache loesen kann
                        -- Daniel Hottinger