Age | Commit message (Collapse) | Author |
|
expose filter_kernels[] and do the table lookup directly
Change-Id: I0b10bff0327c3e01a723736141a9ffd377cd3d20
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
Change-Id: I0ed6de72dc0bb99fc9c5b1f6500399b16754ffb3
|
|
Change-Id: I374fcd8fb45a6893dcdeac6896671be142a99f06
|
|
|
|
|
|
|
|
average improvement ~3x-5x
Change-Id: Iefbcafc05daab77b38a4e63b551e427867a501a4
|
|
Change-Id: I24e10c37ea8f06600cd04b43512efa6170e23e5c
|
|
add one to each entry to remove the universal 'value + 1'.
Change-Id: I8919b1d7fde8155d1728196c4d577db3064e2c1e
|
|
average improvement ~3x-5x
Change-Id: I4cbba2711467b0e205904769ebbb4a1fcbb1a311
|
|
the max value of the lookup in expanded form is:
(((1 << 7) - 1) << 1) - 65 + 1 + 64 = 254
remove the clamp [0, 253] and add one table entry
Change-Id: I0b5d0c66702fdb0b8f1cc9ab9b0dac66326e85a6
|
|
|
|
|
|
|
|
to MB_MODE_INFO_EXT. This saves 36 bytes per 8x8 area for
both the decoder and encoder. (encoder has two MODE_INFO
buffers)
Change-Id: If006abb2224acaf326df3c2be09e77e967662107
|
|
|
|
Cosmetic/Grammatical corrections in vp9 macro comments
Change-Id: I774b983aff854feb69c7e4442e8731ce4c995645
|
|
This commit fixed a mistake in variance calculation.
Thanks to Xintong for spotting the error.
Change-Id: Ia285fc0128c00f0234a73b0a7eba6adc88b8a7de
|
|
average improvement ~4x-5x
Change-Id: Iad9c0a296dbc2ea96d000bd009077999ed58a3c5
|
|
average improvement ~3x-4x
Change-Id: Idbe4d13a00d05ff8be6559b116f416e42c3b4097
|
|
|
|
average improvement ~3x-4x
Change-Id: If0fdcc34b17437a7e3e7fb4caaf1067bc175f291
|
|
Change-Id: I2206ee148a46b234df58f2b623e9f32f26033e04
|
|
Only do the check for resizing if the feature is selected
(i.e., resize_mode = RESIZE_DYNAMIC).
And modify condition for checking to be resize_count >= window,
(since framerate can change).
Change-Id: Idceb4e50956bb965a1492b4993b0dcb393c9be4d
|
|
Change-Id: I123db2d20ae65a10e2dec95eec61150e2f69546d
|
|
|
|
Reduce boost for segment#2 for low bitrates and low-res.
This change is to reduce the rate overshoot at low bitrates.
No change in behavior, except at the very low bitrates.
Change-Id: I0dbd9d3b6356da5804de94adf10fca6a7a8f8948
|
|
~90% faster over 20M pixels
Change-Id: I92d80f66e91e0a870a672cfb5dd29bf1a17cb11a
|
|
average improvement ~2x-3x
Change-Id: I76f7fc00c0ffdf2b4ba41bf3819f3b6044bcdeff
|
|
|
|
Keep the same transform cutoff and partition selection
for speed 5 as in speeds >=6 (non-rd speed settings).
Existing setting for key frame at speed 5 allowed transform size
up to 32x32 on key frames, and did not allow for 4x4 block partition size.
This created more visual artifacts on first few frames.
avgPSNR/overallPSNR/SSIM gains of 0.2/0.7/0.8 for rtc_derf(low-res) set,
and 0/0.7/1.1 gains for rtc set.
Change-Id: I8c139ec6c9bb74e14b4ffbad5f12e94f18a59c0b
|
|
|
|
|
|
and added to MACROBLOCKD.
Change-Id: I0e60aaa9f84bcc9f2376d71bd934f251baee38db
|
|
average improvement ~2x-3x
Change-Id: Idf8be780b8b4228fc91f110a94e4ee1fd9af0163
|
|
|
|
based on ssse3 implementation
~91% faster over 20M pixels
Change-Id: I6d743a53352c2d6de0efe7899d7996e8b0f7fa29
|
|
average improvement ~4x-5x
Change-Id: I37582efc2622bc20b2bf99617a76110ab24e9f6a
|
|
|
|
Change-Id: Icaa643568159c4e2db24eef42090b002ae02a45e
|
|
|
|
For speed 5 real-time mode, the selection of the partition size for
superblocks on the segment (aq-mode=3) uses the non-rd recursive
pick partition search, and can sometimes select 64x64.
For low resolutions, visually better to limit this to 32x32.
Change-Id: I69657a7ed8899f8b3cf8c9c318a2509c5c72c565
|
|
For screen content don't refresh a block at a quantizer higher than
it was last coded at. PReviosuly at realtime speeds the encoder had a
tendency to recode a block from GOLDEN with a higher Q than it was last
coded at.
Change-Id: Iacd561806c769dcce1a81b9827ffc70090f5ba18
|