[MPlayer-users] 2 pass divx encoding from .VOB/dvd - Targeted filesize (bitrate) ends up way way wrong

[Michael Niedermayer]

Hi

On Wednesday 21 August 2002 03:55, D Richard Felker III wrote:
[...]
> > > maybe not. Let me know if you'd like me to try to reproduce it and
> > > I'll see what I can do.
> >
> > yes, a sample which triggers the bug would be nice
> >
> > btw, i did mostly rewrote the rc code in my local tree, its much more
> > flexible now and allso seems to be better than divx5-window$ on a few
> > short testsamples but it isnt bugfree yet :(
>
> From my experience you need LONG samples to judge rate control well.
yes, but i cant test on LONG samples after each small change of the code, and 
as i said there are still problems even with short samples so i do testing 
with short samples until everything works correctly with them and afterwards 
ill try longer samples, i did 2 tests with longer sequences too and they 
seemed to be ok, but i didnt compare them against divx5-win ...

> Would you like me to try to encode a file and upload the results (with
> the stats file), or upload the source vob? Either way it'll be kinda
source vob would be better unless the problem is reproduceable by encoding the 
encoded avi again

> big, so if you prefer I can give you a url to download from not on
well i dont care if mphq or not (if some useable vob is allready available 
somewhere then that would obviously be better)

[...]

Michael