Results 1 to 7 of 7

Thread: Google Releases VP8 Bali Codec SDK

  1. #1
    Join Date
    Jan 2007
    Posts
    15,093

    Default Google Releases VP8 Bali Codec SDK

    Phoronix: Google Releases VP8 Bali Codec SDK

    Google has released a new version of its open VP8 codec. This new version, which is codenamed "Bali", there's a focus on improving the performance and video quality...

    http://www.phoronix.com/vr.php?view=OTE5MQ

  2. #2
    Join Date
    May 2008
    Posts
    73

    Default

    Ehm, no, 7% or 26% is not "much greater" than a 1.3 (or even a 4.5) times improvement. Saying something is 1.3 times faster is the same as a 30% (or 33.333333% or something similar) improvement.

  3. #3
    Join Date
    Apr 2010
    Posts
    99

    Default

    Quote Originally Posted by quintesse View Post
    Ehm, no, 7% or 26% is not "much greater" than a 1.3 (or even a 4.5) times improvement. Saying something is 1.3 times faster is the same as a 30% (or 33.333333% or something similar) improvement.
    My thoughts exactly.
    Michael, can you elaborate on this? Is it a typo?

  4. #4
    Join Date
    Mar 2011
    Posts
    13

    Default and ffmpeg one?

    I know that ffmpeg guy have done an other one which was really fast.
    So what is the winner between ffvp8 and libvpx?

  5. #5
    Join Date
    Jan 2007
    Location
    Germany
    Posts
    2,155

    Default

    Quote Originally Posted by dufoli View Post
    I know that ffmpeg guy have done an other one which was really fast.
    So what is the winner between ffvp8 and libvpx?
    ffvp8 is only a decoder. The new libvpx release brings lots of encoder improvements.

  6. #6
    Join Date
    Jan 2010
    Posts
    365

    Default

    I'd be pretty cool if VP8 guys would stop caring about crappy metrics like PSNR for video quality.

  7. #7
    Join Date
    May 2010
    Posts
    187

    Default

    Quote Originally Posted by DeiF View Post
    My thoughts exactly.
    Michael, can you elaborate on this? Is it a typo?
    Looks like he wrote it in haste.. A quick click on the link to the blog shows where he got his figures.

    "Best" mode average encoding speed: On x86 processors, Bali runs 4.5x as fast than our initial release and 1.35x faster than Aylesbury.
    "Good" mode average encoding speed: Bali is 2.7x faster than our initial release and 1.4x faster than Aylesbury.
    On ARM platforms with Neon extensions, real-time encoding of video telephony content is 7% faster than Aylesbury on single core ARM Cortex A9, 15% on dual-core and 26% on quad core.
    On the NVidia Tegra2 platform, real time encoding is 21-36% faster than Aylesbury, depending on encoding parameters.
    "Best" mode average quality improved 6.3% over Aylesbury using the PSNR metric.
    "Best" mode average quality improved 6.1% over Aylesbury using the SSIM metric.
    So they're talking about different settings.. Best, good and real-time encoding.

Posting Permissions

  • You may not post new threads
  • You may not post replies
  • You may not post attachments
  • You may not edit your posts
  •