SIF1 on the Map

Via the MultimediaWiki, Suxen Drol made me aware of recent video codec identified only as SIF1. It seems the codec has been on the radar for a few months now. The decoder source code (Windows) is available for download, as are a bunch of samples. Is anyone interested in writing a proper description for this codec based on the source code? If so, I hope you can understand whatever (human) language the author wrote it in. Here are the core filenames:

$ wc *.cpp
    1185    2217   37009 AdaptFiltrDequant.cpp
    4375   13045  119493 BikubDetcimation.cpp
   14075   42529  533493 DeblokFiltrCompDvij.cpp
    1566    3110   57229 MotionArifmDecomp.cpp
     820    2429   23311 Rgb_viu_kon.cpp
   21588   70557  889709 SifDecompressor.cpp
     118     408    3577 SifEkspotrFunk.cpp
     394    1063   12274 SifFilter.cpp
      96     323    2764 SifFiltrUprDialog.cpp
   44217  135681 1678859 total

Okay, so maybe not all of those filenames are so bad, but I challenge you to decipher many of the identifiers in the source. Also, some of those files are a tad bulky. Large swaths of code are written only in inline MMX. I haven’t seen this since Lagarith. I have this weird feeling that this codec is going to exist in its own little universe for a long time to come even though the author seems to have invested a lot of research into making it competitive with H.264.

8 thoughts on “SIF1 on the Map”

  1. Kostya

    Codec author used inhuman language called Russian and since English knowledge in those parts of world is not very good to put it mildly, he used Latin letters for Russian names transcription.

    But in your case most names are readable because of common origin (i.e. “Arifm” for “Arithmetic”). MÃ¥ns RullgÃ¥rd can help you with deciphering.

  2. nine

    The dude has also posted a few times on doom10 (maybe 9 as well?) if you wanted to find him to talk about it.

  4. Multimedia Mike Post author

    @Peter: Oh, the comments are there, but they show up something like this:

    // Ðàçìåòêà óïðàâëÿþùèõ áèòîâ 1-Âåðõíÿÿ

    I suppose I could trial-and-error my way to the right character encoding, but… why?

  5. Mans

    I’d try KOI8 first. Unless you know Russian, there’s probably not much point though. Kostya, I think you’ll have to step in here.

  6. Michael Kostylev

    > Otherwise nobody will protect me if Microsoft release a codec which will be based on SIF technologies.

    Mania grandiosa confirmed.

    > // Ðàçìåòêà óïðàâëÿþùèõ áèòîâ 1-Âåðõíÿÿ

    No doubt, cp1251.

  7. Kostya

    After iconv-ing it a bit from cp1251 I got “Разметка управляющих битов 1-Верхняя” which means “Control bits marking 1-Top”.

    @Mans: while KOI-8 was a standard in USSR now most people in Russia use windows-1251 codepage (piracy may be a factor here), KOI-8 is for old Unix admins now.

    Anyway, if you need that translated, just ask.

  8. Multimedia Mike Post author

    Thanks, Kostya. What I copy & pasted was only part of a longer comment, so it makes even less sense out of context. I don’t think this codec will be my highest priority (technically, highest priority needs to be FATE, then of course WC4 Xan :-) ).

Comments are closed.