View Single Post
Old 13th December 2018, 21:16   #1318  |  Link
benwaggoner
Moderator
 
Join Date: Jan 2006
Location: Portland, OR
Posts: 4,752
Quote:
Originally Posted by Beelzebubu View Post
TBH, from what I understand from people in the relevant committees, this was proposed for HEVC also. The reason they didn't do it had nothing to do with HW, though, but was simply to keep the VoD and RTC use cases technically more similar. (Entropy dependencies are obviously disabled for RTC use cases.)
For RTC you could have backwards entropy states just fine, I think. So IPPPPPP could have each P reference the entropy state of the previous P. Error correction for lost packets would require trickiness. AV1 RTC would have the same issues.

Limiting entropy state reference to reference frames/tiles would be a lot more robust, but of reduce value. A bunch of non-ref b frames referencing the same frames probably have a lot more in common than any do to the ref-B/P/I frames they reference...

Random access would also be slowed by interframe entropy coding; it's essentially adding another layer of reference dependencies. Entropy is easier to decode, but getting to an arbitrary frame in a long GOP could require decoding the entropy state of a lot more frames than it would with a traditional IbBbP with inter-frame entropy only. With 8 b-frames, getting to an arbitrary frame of H.264/HEVC requires decoding about 1/8th of frames between the IDR and the target frame. Seems like it could be a lot worse in AV1, if I am understanding correctly.
__________________
Ben Waggoner
Principal Video Specialist, Amazon Prime Video

My Compression Book
benwaggoner is offline   Reply With Quote