Jingning Han [Mon, 16 Mar 2015 19:03:31 +0000 (12:03 -0700)]
Refactor column integral projection computation
Move the scaling factor outside column projection. This avoids
repeated calculation of the same scaling factor. Profiling shows
that the percentage of vp9_int_pro_col_sse2 of overall cycles
goes from 2.29% down to 1.88%.
Yaowu Xu [Mon, 16 Mar 2015 16:42:33 +0000 (09:42 -0700)]
vp9_pick_inter_mode(): minor optimizations
1. remove duplicate initialization to mbmi->interp_filter.
2. move mv clamping into ref_frame loop instead of mode checking loop.
3. move the check if last frame is same as golden frame earlier to
avoid initialization of Golden reference related variables.
James Zern [Sat, 14 Mar 2015 01:52:11 +0000 (18:52 -0700)]
usage.dox: fix encoder/decoder subpage list indent
use \li to separate the list items contained in conditionals. this
avoids the encode page becoming a sub-item of decode; likely a problem
in <1.8.3.
+ fix encoder conditional, spelling error
+ correct encode page name to match decode 'Encoding'
James Zern [Sat, 14 Mar 2015 01:49:03 +0000 (18:49 -0700)]
usage.dox: fix doxygen warnings in 1.8.x
use \li to denote list items with \if.
fixes the following likely visible in <1.8.3:
usage.dox: warning: Invalid list item found
usage.dox: warning: End of list marker found without any preceding list items
Jingning Han [Fri, 13 Mar 2015 23:51:29 +0000 (16:51 -0700)]
Fix choose_partitioning threshold setup for speed -5
The compression performance of speed -5 is on average 12.6% better
than speed -6. At lower bit-rates, the gains are typically 20% or
more. For 2-thread encoding, the speed -5 takes about 1.6x time of
speed -6.
Yaowu Xu [Fri, 13 Mar 2015 01:14:43 +0000 (18:14 -0700)]
Added comment for vp9 only codec controls
Comments are updated to reflect that these controls apply to VP9 only,
thereby, to insure the document produced by doxygent to reflect the
same fact too.
Jingning Han [Thu, 12 Mar 2015 23:18:12 +0000 (16:18 -0700)]
Reduce the number of full block SAD calls
This commit uses a 6-point 1-step refine motion search in the
integral projection based full pixel motion estimation, to replace
the current 9-point search.
It reduces runtime cost of speed -6 on some noisy clips, e.g.,
dark720p single thread
33314 b/f, 40.076 dB, 18231 ms ->
33307 b/f, 40.067 dB, 17768 ms
The compression performance for rtc set remains unchanged.
Yaowu Xu [Wed, 11 Mar 2015 17:16:39 +0000 (10:16 -0700)]
vp9_pick_inter_mode(): Use single loop to evaluate inter modes
This commit changes to use single loop to evaluate all inter modes.
There is no impact on compression quality and speed, but allow future
experiment with the order of modes evaluated.
Yunqing Wang [Wed, 11 Mar 2015 18:31:47 +0000 (11:31 -0700)]
Minorly modify model_rd_for_sb_y function
Added a skip_dc check. If skip_dc = 1, we could eliminate calling
of vp9_model_rd_from_var_lapndz(). This gave slight PSNR & SSIM
gain(<0.1%), and no speed change.
Jingning Han [Wed, 11 Mar 2015 23:08:59 +0000 (16:08 -0700)]
Remove unnecessary speed feature checking
This commit removes the pred_mv_sad comparison from rtc motion
search, given that a stronger comparison has been done at the
mode search level to eliminate unlikely selected reference frames.
Jingning Han [Tue, 10 Mar 2015 01:55:38 +0000 (18:55 -0700)]
Apply fast motion search to golden reference frame
This commit enables the rtc coding mode to run integral projection
based motion search for golden reference frame. It improves the
speed -6 compression performance by 1.1% on average, 3.46% for
jimred_vga, 6.46% for tacomascmvvga, and 0.5% for vidyo clips. The
speed -6 is about 6% slower.
Jingning Han [Wed, 11 Mar 2015 22:44:26 +0000 (15:44 -0700)]
Refactor to remove GLOBAL_MOTION
Make the vp9_int_pro_motion_estimation() function return zero
motion vector if high bit depth is turned on, instead of removing
it from compiled codes.
paulwilkins [Fri, 6 Mar 2015 16:32:20 +0000 (16:32 +0000)]
Shorten GF/arf interval in hard scenes.
This patch accounts in the first pass stats for blocks that
while not coded as intra, are complex and have an intra error /
best error ratio below a threshold.
The modification shortens the GF arf interval for a particular
class of content that contains a lot of blocks matching the
above criteria. (In one short problem test sequence the average
interval dropped from about 14-15 to 10-11)
The change results in small net gains in metrics results for the
Yt(~0.2%) and yt-hd (~0.5%) sets and is approximately neutral
for the other test sets.
The change is currently shielded by a flag and off by default
pending verification that it does not cause other regressions
in tests on a wider YT test set.
Yaowu Xu [Wed, 11 Mar 2015 02:06:52 +0000 (19:06 -0700)]
Separate rd_thresh adaption by ref_frame
Only update the rd_thresh factors for modes sharing same reference
frame. This helps overall compression of 6 and 7 by .13% and .19%
respectively without any noticeable speed difference.
Marco [Fri, 6 Mar 2015 01:26:52 +0000 (17:26 -0800)]
Modify update golden reference update under aq-mode=3 mode.
For non-SVC 1 pass CBR: make the GF update interval a multiple of the
cyclic refresh period, and use encoding stats to prevent GF update at certain times.
Yaowu Xu [Fri, 6 Mar 2015 21:45:39 +0000 (13:45 -0800)]
Enable using Golden reference in choose_partition()
Choose_partition uses only the last frame as reference frame in making
partition decision, this commit adds the check on how well Golden
frame with (0,0) predicts the current block, and uses GF(0,0) as
basis for partition decision if it produces better prediction.
The commit improves rtc speed 6 and 7 encoding by 0.14% and 0.19%
respectively.
Jingning Han [Mon, 9 Mar 2015 17:59:29 +0000 (10:59 -0700)]
Skip golden ref frame check when it is same as last ref frame
When golden reference frame is refreshed, the next frame has both
its last and golden reference frames point to the same reference
frame in real-time coding mode. Experiments suggest that using
two separate reference frames for frames right after golden refresh
frame does not provide further compression performance advantage.
This commit hence retains the current encoder implementation and
shuts off the mode search over golden reference frame in this case.
It makes the encoder run slightly faster at no coding performance
change.
Yunqing Wang [Fri, 6 Mar 2015 23:17:59 +0000 (15:17 -0800)]
vp9_ethread: fix me consts initialization to support aq_mode=3 encoding
While turning on "--aq_mode=3", the quantizers are updated by each
thread. Fixed the me consts initialization function to make sure
that the correct thread data are updated.
Yunqing Wang [Thu, 5 Mar 2015 17:44:18 +0000 (09:44 -0800)]
Modify the setting of transform skip flags in non-rd mode
While searching for the best mode in non-rd case, SSE of
a partition block is calculated and the transform size is set.
This patch rewrites the skip checking conditions based on
transform size instead of partition size to be more precise.
Small gains were seen in rtc set borg test (speed 6).
AVG PSNR: 0.087%, overall PSNR: 0.073%, SSIM: 0.146%.
No noticeable speed change.
projects / libvpx / log