- Using multiplication and shifting instead of division in
intra prediction.
- Maximum absolute difference is 1 for division statements
in d45, d27, d63 prediction modes. However, errors can
cumulate for large block sizes when using already predicted
values.
- Maximum number of non-matching result values in loops using
division are:
4x4 0/16
8x8 0/64
16x16 10/256
32x32 13/1024
64x64 122/4096
Overall PSNR
derf: 0.005
yt: -0.022
std-hd: 0.021
hd: -0.006
Change-Id: I3979a02eb6351636442c1af1e23d6c4e6ec1d01d
rebased.
This patch includes 16x16 butterfly inverse ADST/DCT hybrid
transform. It uses the variant ADST of kernel
sin((2k+1)*(2n+1)/4N),
which allows a butterfly implementation.
The coding gains as compared to DCT 16x16 are about 0.1% for
both derf and std-hd. It is noteworthy that for std-hd sets
many sequences gains about 0.5%, some 0.2%. There are also few
points that provides -1% to -3% performance. Hence the average
goes to about 0.1%.
Change-Id: Ie80ac84cf403390f6e5d282caa58723739e5ec17
The commit changes the coding mode to lossless whenever the lowest
quantizer is choosen.
As expected, test results showed no difference for cif and std-hd
set where Q0 is rarely used. For yt and yt-hd set, Q0 is used for
a number of clips, where this commit helped a lot in the high end.
Average over all clips in the sets:
yt: 2.391% 1.017% 1.066%
hd: 1.937% .764% .787%
Change-Id: I9fa9df8646fd70cb09ffe9e4202b86b67da16765
Since there is no Y2, these values are always zero. This changes the
bitstream results slightly, hence a separate commit.
Change-Id: I2f838f184341868f35113ec77ca89da53c4644e0
These allow sending partial bitstream packets over the network before
encoding a complete frame is completed, thus lowering end-to-end
latency. The tile-rows are not independent.
Change-Id: I99986595cbcbff9153e2a14f49b4aa7dee4768e2
Since addition of the larger-scale transforms (16x16, 32x32), these
don't give a benefit at macroblock-sizes anymore. At superblock-sizes,
2nd-order transform was never used over the larger transforms. Future
work should test whether there is a benefit for that use case.
Change-Id: I90cadfc42befaf201de3eb0c4f7330c56e33330a
This patch abstracts the selection of the coefficient band
context into a function as a precursor to further experiments
with the coefficient context.
It also removes the large per TX size coefficient band structures
and uses a single matrix for all block sizes within the test function.
This may have an impact on quality (results to follow) but is only an
intermediate step in the process of redefining the context. Also the
quality impact will be larger initially because the default tables will
be out of step with the new banding.
In particular the 4x4 will in this case only use 7 bands. If needed we
can add back block size dependency localized within the function, but
this can follow on after the other changes to the definition of the
context.
Change-Id: Id7009c2f4f9bb1d02b861af85fd8223d4285bde5
This is an initial step to facilitate experimentation
with changes to the prior token context used to code
coefficients to take better account of the energy of
preceding tokens.
This patch merely abstracts the selection of context into
two functions and does not alter the output.
Change-Id: I117fff0b49c61da83aed641e36620442f86def86
1. Added a bit in frame header to to indicate if a frame is encoded
in lossless mode, so decoder does not make the decision based on Q0
2. Minor changes to make sure that lossy coding works same as when
the lossless experiment is not enabled.
3. Renamed function pointers for transforms to be consistent, using
prefix fwd_txm and inv_txm for forward and inverse respectively
To encode in lossless mode, using "--lossless=1 --min-q=0 --max-q=0"
with vpxenc.
Change-Id: Ifae53b26d2ffbe378d707e29d96817b8a5e6c068
Initial ssse3 convolve avg functions and is one step closer
to using x86inc.asm. The decoder performance improved by 8% for
the test clip used. This should be revisited later to see if
averaging outside the loop is better than having many similar
filter functions.
Change-Id: Ice3fafb423b02710b0448ffca18b296bcac649e9
Removal of the NEWCOEFCONTEXT experiment to
reduce code clutter and make it easier to experiment with
some other changes to the coefficient coding context.
Change-Id: Icd17b421384c354df6117cc714747647c5eb7e98
This is after discussion with the hardware team. Update the unit test
to take these sizes into account. Split out some duplicate code into
a separate file so it can be shared.
Change-Id: I8311d11b0191d8bb37e8eb4ac962beb217e1bff5
Implement convolve8_avg using common functions which are already optimized
instead of using more obscure ones which have only C versions. Encoder
overall speed-up of about 12%.
Change-Id: I8c57aa76936c8a48f22b115f19f61d9f2ae1e4b6
fixed format issues.
Implement the inverse 4x4 ADST using 9 multiplications. For this
particular dimension, the original ADST transform can be
factorized into simpler operations, hence is retained.
Change-Id: Ie5d9749942468df299ab74e90d92cd899569e960
A 16 bit overflow condition occurs when using the EIGHTTAP_SMOOTH filters.
(vp9_sub_pel_filters_8lp) Changed the order of the adds to fix this problem.
Also added ssse3 support for 4x4 subpixel filtering.
Change-Id: I475eaadae920794c2de5e01e9735c059a856518e
Replace as_mv.{first, second} with a two element array, so that they
can easily be processed with an index variable.
Change-Id: I1e429155544d2a94a5b72a5b467c53d8b8728190
Also port the 4x4, 16x16, 8x16 and 16x8 versions to x86inc.asm; this
makes them all slightly faster, particularly on x86-64. Remove SSE3
sad16x16 version, since the SSE2 version is now faster.
About 1.5% overall encoding speedup.
Change-Id: Id4011a78cce7839f554b301d0800d5ca021af797
Pass the current mb row and column around rather than the
recon_yoffset and recon_uvoffset, since those offsets will
change from predictor to predictor, based on the reference
frame selection.
Change-Id: If3f9df059e00f5048ca729d3d083ff428e1859c1
This commit adds the 8 tap SSSE3 subpixel filters back into the code
underneath the convolve API. The C code is still called for 4x4
blocks, as well as compound prediction modes. This restores the
encode performance to be within about 8% of the baseline.
Change-Id: Ife0d81477075ae33c05b53c65003951efdc8b09c
Tweak to default mode context to account for the fact
that when there are no non zero motion candidates
Nearest is now the preferred mode for coding a 0,0
vector.
Also resolve duplicate function name and typos.
Change-Id: I76802788d46c84e3d1c771be216a537ab7b12817
Refactor the 8x8 inverse hybrid transform. It is now consistent
with the new inverse DCT. Overall performance loss (due to the
use of this variant ADST, and the rounding errors in the butterfly
implementation) for std-hd is -0.02.
Fixed BUILD warning.
Devise a variant of the original ADST, which allows butterfly
computation structure. This new transform has kernel of the
form: sin((2k+1)*(2n+1) / (4N)). One of its butterfly structures
using floating-point multiplications was reported in Z. Wang,
"Fast algorithms for the discrete W transform and for the discrete
Fourier transform", IEEE Trans. on ASSP, 1984.
This patch includes the butterfly implementation of the inverse
ADST/DCT hybrid transform of dimension 8x8.
Change-Id: I3533cb715f749343a80b9087ce34b3e776d1581d
This patch adds column-based tiling. The idea is to make each tile
independently decodable (after reading the common frame header) and
also independendly encodable (minus within-frame cost adjustments in
the RD loop) to speed-up hardware & software en/decoders if they used
multi-threading. Column-based tiling has the added advantage (over
other tiling methods) that it minimizes realtime use-case latency,
since all threads can start encoding data as soon as the first SB-row
worth of data is available to the encoder.
There is some test code that does random tile ordering in the decoder,
to confirm that each tile is indeed independently decodable from other
tiles in the same frame. At tile edges, all contexts assume default
values (i.e. 0, 0 motion vector, no coefficients, DC intra4x4 mode),
and motion vector search and ordering do not cross tiles in the same
frame.
t log
Tile independence is not maintained between frames ATM, i.e. tile 0 of
frame 1 is free to use motion vectors that point into any tile of frame
0. We support 1 (i.e. no tiling), 2 or 4 column-tiles.
The loopfilter crosses tile boundaries. I discussed this briefly with Aki
and he says that's OK. An in-loop loopfilter would need to do some sync
between tile threads, but that shouldn't be a big issue.
Resuls: with tiling disabled, we go up slightly because of improved edge
use in the intra4x4 prediction. With 2 tiles, we lose about ~1% on derf,
~0.35% on HD and ~0.55% on STD/HD. With 4 tiles, we lose another ~1.5%
on derf ~0.77% on HD and ~0.85% on STD/HD. Most of this loss is
concentrated in the low-bitrate end of clips, and most of it is because
of the loss of edges at tile boundaries and the resulting loss of intra
predictors.
TODO:
- more tiles (perhaps allow row-based tiling also, and max. 8 tiles)?
- maybe optionally (for EC purposes), motion vectors themselves
should not cross tile edges, or we should emulate such borders as
if they were off-frame, to limit error propagation to within one
tile only. This doesn't have to be the default behaviour but could
be an optional bitstream flag.
Change-Id: I5951c3a0742a767b20bc9fb5af685d9892c2c96f
Update the code to call the new convolution functions to do subpixel
prediction rather than the existing functions. Remove the old C and
assembly code, since it is unused. This causes a 50% performance
reduction on the decoder, but that will be resolved when the asm for
the new functions is available.
There is no consensus for whether 6-tap or 2-tap predictors will be
supported in the final codec, so these filters are implemented in
terms of the 8-tap code, so that quality testing of these modes
can continue. Implementing the lower complexity algorithms is a
simple exercise, should it be necessary.
This code produces slightly better results in the EIGHTTAP_SMOOTH
case, since the filter is now applied in only one direction when
the subpel motion is only in one direction. Like the previous code,
the filtering is skipped entirely on full-pel MVs. This combination
seems to give the best quality gains, but this may be indicative of a
bug in the encoder's filter selection, since the encoder could
achieve the result of skipping the filtering on full-pel by selecting
one of the other filters. This should be revisited.
Quality gains on derf positive on almost all clips. The only clip
that seemed to be hurt at all datarates was football
(-0.115% PSNR average, -0.587% min). Overall averages 0.375% PSNR,
0.347% SSIM.
Change-Id: I7d469716091b1d89b4b08adde5863999319d69ff
This commit introduces a new convolution function which will be used to
replace the existing subpixel interpolation functions. It is much the
same as the existing functions, but allows for changing the filter
kernel on a per-pixel basis, and doesn't bake in knowledge of the
filter to be applied or the size of the resulting block into the
function name.
Replacing the existing subpel filters will come in a later commit.
Change-Id: Ic9a5615f2f456cb77f96741856fc650d6d78bb91
This commit changes the 4x4 iDCT to use same algorithm & constants as
other iDCTs. The 4x4 fDCT is also changed to be based on the new iDCT.
Change-Id: Ib1a902693228af903862e1f5a08078c36f2089b0
This commit makes the NearestMV match the chosen
best reference MV. It can be a 0,0 or non zero vector
which means the the compound nearest mv mode can
combine a 0,0 and a non zero vector.
Change-Id: I2213d09996ae2916e53e6458d7d110350dcffd7a
and called this function in vp9_dequant_idct_add_32x32_c when
eob == 1. For the test clip used, the decoder performance improved
by 21+%. Based on Yaowu's 16 point idct work.
Change-Id: Ib579a90fed531d45777980e04bf0c9b23c093c43
fixed a function prototypes to prevent compiler warnings;
removed a function not in use;
un-capitialize "Refstride" to ref_stride
Change-Id: Ib4472b6084f357d96328c6a06e795b6813a9edba
This commit changes the inverse 16 point dct to use the same algorithm
as the one for 32 point idct. In fact, now 16 point dct uses the exact
version of the souce code for even portion of the 32 point idct.
Tests showed current implementation has significant better accuracy
than the previous version. With this implementation and the minor bug
fix on forward 16 point dct, encoding tests showed about 0.2% better
compression of CIF set, test results on std-hd setting pending.
Change-Id: I68224b60c816ba03434e9f08bee147c7e344fb63
This commit changes the 32x32 idct to use integer only. The algorithm
was taken directly from "A Fast Computational Algorithm for the
Discrete Cosine Tranform" by W. Chen, et al., which was published in
IEEE Transaction on Communication Vol. Com.-25 No. 9, 1977. The signal
flow graph in the original paper is for a 32 point forward dct, the
current implementation of inverse DCT was done by follow the graph in
reversed direction.
With this implementation, the 32 point inverse dct contains a 16 point
inverse dct in its even portion, similarly the 16 point idct further
contains 8 point and 4 point inverse dcts.
As of patch 4, encoding tests showed there is no compression loss when
compared against the floating point baseline. Numbers even showed very
small postives. (cif: .01%, std-hd: .05%).
Change-Id: I2d2d17a424b0b04b42422ef33ec53f5802b0f378
Adds a special combination mode specific to intra prediciton
mode D45.
Current results with the compound inter/intra experiment:
derf: 0.2%
yt: 0.55%
std-hd: 0.75%
hd: 0.74%
Change-Id: I8976bdf3b9b0b66ab8c5c628bbc62c14fc72ca86
First step in simplifying the segment mode and
segment EOB flags into a simpler segment skip
flag that implies 0,0 mv and EOB at position 0.
Change-Id: Ib750cac31a7a02dc21082580498efd9f7d8d72a5
We'd backup and restore all cols for a 64x64 SB, but the array wouldn't
be big enough to hold all that data.
Change-Id: Ic68ea721bf07e0b2f3937bd16b0b734bcc743ce1
Adds a flag to disable features that would inhibit frame parallel
decoding. This includes backward adaptation and MV sorting based
on search in ref frame buffer.
Also includes some minor clean-ups.
Change-Id: I434846717a47b7bcb244b37ea670c5cdf776f14d
Adds an error-resilient mode where frames can be continued
to be decoded even when there are errors (due to network losses)
on a prior frame. Specifically, backward updates are turned off
and probabilities of various symbols are reset to defaults at
the beginning of each frame. Further, the last frame's mvs are
not used for the mv reference list, and the sorting of the
initial list based on search on previous frames is turned off
as well.
Also adds a test where an arbitrary set of frames are skipped
from decoding to simulate errors. The test verifies (1) that if
the error frames are droppable - i.e. frame buffer updates have
been turned off - there are no mismatch errors for the remaining
frames after the error frames; and (2) if the error-frames are non
droppable, there are not only no decoding errors but the mismatch
PSNR between the decoder's version of the post-error frames and the
encoder's version is at least 20 dB.
Change-Id: Ie6e2bcd436b1e8643270356d3a930e8989ff52a5
Updated the instrinsic code to match Yaowu's latest loopfilter change.
(I584393906c4f5f948a581d6590959522572743bb)
The decoder performance improved by ~30% for the test clip used.
Change-Id: I026cfc75d5bcb7d8d58be6f0440ac9e126ef39d2
* changes:
Use alt-ref frame context for keyframes
Preserve the previous golden frame on golden updates
Generalize and increase frame coding contexts
Start to anonymize reference frames
Update encoder to use fb_idx_ref_cnt
Remove buffer-to-buffer copy logic
The loop filtering used for MB edge or internal edge of a MB using 8x8
tranform was reading 5 pixel each side and writting 3 pixel each side.
With suggestion from Aki and Scott on hardware&software performance,
this commit changed to read 4 pixel each side and write 3 pixel each
side.
Change-Id: I584393906c4f5f948a581d6590959522572743bb
This commit restores the quality lost when the buffer-to-buffer copy
logic was removed. Note that this is specific to the current use of
golden frames and will need rework when RTC functionality is added.
Change-Id: I7324a75acd96eafd9e0f9b8633d782e390d5dc21
Previously there were two frame coding contexts tracked, one for normal
frames and one for alt-ref frames. Generalize this by signalling the
context to use in the bitstream, rather than tieing it to the alt ref
refresh bit. Also increase the number of contexts available to 4, which
may be useful for temporal scalability.
Change-Id: I7b66daaddd55c535c20cd16713541fab182b1662
Remove lst_fb_idx, gld_fb_idx, alt_fb_idx, refresh_last_frame,
refresh_golden_frame, refresh_alt_ref_frame from common. Gold/Alt are
encode side conventions. From the decoder's perspective, we want to be
dealing with numbered references.
Updates to active_ref 2 signal mode context switches, vestigial from
refresh_alt_ref_frame. This needs some clean up to make sense with
increased numbers of reference frames, as well as reimplementing the
swapping of alt/golden which was previously done using the
buffer-to-buffer copy mechanism removed in an earlier commit.
Change-Id: I7334445158b7666f9295d2a2dd22aa03f4485f58
Do reference counting the same way on the encoder as the decoder does,
rather than maintaining the 'flags' member of YV12_BUFFER_CONFIG.
Change-Id: I91dc210ffca081acaf9d5c09a06e7461b3c3139c
This is the first in a series of commits to add additional reference
frames to the codec. Each frame will be able to update any of the
available references, but copying between references is not
supported.
Change-Id: I5945b5ce6cc3582c495102b4e7eed4f08c44d5a1
Uses a single 1D table to implement the weighting of the predictors
for the compound inter-intra experiment.
Change-Id: I204ffbe4f9fc79d5d43b6c724ad253d800461012
These variables have the type int64_t, not long long. long long could
be a larger type than 64 bits. Emulate INT64_MAX for older versions of
MSVC, and remove the unreferenced vpx_ports/vpxtypes.h
Change-Id: Ideaca71838fcd3849d816d5ab17aa347c97d03b0
This experiment gives little gains and adds relatively much code
complexity (and it hinders other experiments), so let's get rid of
it.
Change-Id: Id25e79a137a1b8a01138aa27a1fa0ba4a2df274a
In commit 9a1d73d, loop filtering was added for UV 4x4 boundaries
when TX_8X8 is used by a MB. This commit further refined the decision
to be based on the actual transform used for the UV planes. When
UV planes use 4x4 transform, i.e. when prediction mode used is either
I8X8_PRED or SPLITMV, UV planes are filtered on 4x4 boundaries, and no
filtering is applied on 4x4 block boundaries when UV planes use 8X8
transform.
Change-Id: Ibb404face0a1d129b4b4abaf67c55d82e8df8bec
Fixes some scaling issues. Adds an option to only compute the
dct on the low-low subband for 32x32 and 64x64 blocks using
only a single 16x16 dct after 1 and 2 wavelet decomposition
levels respectively. Also adds an option to use a 8x8 dct
as building block.
Currenlty with the 2/6 filter and with a single 16x16 dct on
the low low band, the reuslts compared to full 32x32 dct is
as follows:
derf: -0.15%
yt: -0.29%
std-hd: -0.18%
hd: -0.6%
These are my current recommended settings, since the 2/6 filter
is very simple.
Results with 8x8 dct are about 0.3% worse.
Change-Id: I00100cdc96e32deced591985785ef0d06f325e44
and vp9_mb_lpf_vertical_edge_w_sse2. This was quickly done so we can
run some tests over the weekend. Future commits will optimize/refactor these
functions further.
The decoder performance improved by ~17% for the clip used.
Change-Id: I612687cd5a7670ee840a0cbc3c68dc2b84d4af76
Updated the rtcd_defs and used the sse2 uv version
of the loopfilter. The performance improved by ~8%
for the test clip used.
Change-Id: I5a0bca3b6674198d40ca4a77b8cc722ddde79c36
The commit changed to not to use wider lpf within a superblock when
32x32 transform is used for the block.
The commit also changed to use the shorter version of loop filtering:
for UV planes.
Change-Id: I344c1fb9a3be9d1200782a788bcb0b001fedcff8
