Help us keep the list up to date and submit new video software here.
Tool
Complete Version history / Release notes / Changelog / What's New for Kvazaar
v2.3.2
Features
There are no major new features, but several fixes, most notably to 10 bit encoding and cost calculation for smp and amp blocks. Due to the fixes to amp cost calculation, amp is now enabled on veryslow preset.
Impact of fixes on the old veryslow preset
SequencesBD-BR (PSNR)BD-BR (SSIM)Speed
hevc-A-1.2 %-1.4 %0.96×
hevc-B-1.4 %-1.6 %0.97×
hevc-C-1.2 %-1.4 %0.97×
hevc-D-1.3 %-1.6 %0.98×
hevc-E-0.9 %-1.0 %1.00×
hevc-F-1.1 %-1.4 %0.98×
Overall-1.2 %-1.4 %0.98×
Veryslow of v2.3.1 vs v2.3.2
SequencesBD-BR (PSNR)BD-BR (SSIM)Speed
hevc-A-3.1 %-3.5 %0.69×
hevc-B-3.0 %-3.2 %0.72×
hevc-C-2.9 %-3.3 %0.78×
hevc-D-2.9 %-3.3 %0.82×
hevc-E-2.3 %-2.1 %0.83×
hevc-F-2.4 %-2.8 %0.79×
Overall-2.7 %-3.0 %0.77×
To other presets the impact of fixes is smaller
Fixes
Several fixes to 10 bit encoding
Fix SATD calculation 36f7752
Ensure proper stack size 1eeccb3
Fix typing for threadwrapper a7aeb23
Separate .pdb files for exe and library ccc643c
Fix y4m reading 4aeeba7 b8d9185
Update minimum CMake version 3393d56
Fix --no-early-skip d1e11d8
Fix lossless incorrectly selecting skip d1e11d8
Rate control improvements 526c8db 999c512
Fix bit cost calculation for tr splits and smp 6957cea
Update the default configuration to match the medium preset 3eed14d
External contributions
add missing files in distribution for compilation with cmake by @vtorri in #402
encmain.c: guard WINVER and _WIN32_WINNT macros by @vtorri in #405
ax_pthread/clang: move -pthread to LIBS by @1480c1 in #407
fix ios build by @trittsv in #416
fix android build by @trittsv in #415
Fix Windows ARM64 builds when using MSVC by @anthony-linaro in #419
Fix emscripten build by @meowtec in #422
Add BSDs to exclusion list for compiler flag with cmake by @rhelmot in #426
Avoid double free of roi.file_path by @bart-kroon in #428
Fix passing too many arguments to "init_test_strategies". by @fancycode in #440
V2.3.1
Features
New AVX2 optimizations for intra angular predictions, faster and gets around a code generation issue with MSVC > 19.36
Fixes
Several fixes to CMakeLists.txt
fix unaligned access on array_checksum_generic8 c6f2ba4
fix preset log while enable-logging to false 7424474
Include CMakeLists.txt in dist 3b1bcb6
External contributions
Fix typo in error message. by @fancycode in #386
Minor cmake fixes by @lgbaldoni and @kmilos in #385
Ignore "*get_pc_thunk.*" symbols in exported symbols test by @matoro in #392
Fixed issue #394 - missing _mm256_storeu2_m128i macro by @supersjgk in #395
New Contributors
@fancycode made their first contribution in #386
@lgbaldoni made their first contribution in #385
@supersjgk made their first contribution in #395
Performance
With the new AVX2 intra prediction the encoder is 1-5% faster, depending on settings
Full Changelog: v2.3.0...v2.3.1
Contributors
@fancycode
@lgbaldoni
@kmilos
@matoro
@supersjgk
fancycode, lgbaldoni, and 3 other contributors
Assets
7
3 people reacted
V2.3.0
Jan 17, 2024
@Jovasa Jovasa
v2.3.0
e8be7ac
V2.3.0
Features
--(no-)enable-logging to enable/disable logging of normal encoder perfomance into stderr, errors are still outputted to stderr.
AVX2 optimisations for finding last non zero coefficient in RDOQ
Remove YASM to make compilation with visual studio easier
Experimental support for CMake, in the future we would like to get rid of automake and visual studio so if there are any issues with the CMakeLists.txt please report them
Fixes
Fix a bug when requesting encoder_headers before any frame has been pushed in aaae5b0
Fix a problem with win+gcc (mingw, msys, cygwin) causing some optimized functions to segfault 589ed47
Fix GCC detection for automake 49dc5fc 8523c96
External contributions
add config option to turn off logging output (#356) by @farindk in #357
Update Dockerfile base image to Ubuntu 20.04 by @PeterDaveHello in #358
threads.h: fix for older macOS builds by @barracuda156 in #373
Don't export MD5 byteReverse symbol on big-endian by @matoro in #377
New Contributors
@farindk made their first contribution in #357
@barracuda156 made their first contribution in #373
@matoro made their first contribution in #377
Performance
The RD performance should be exactly the same as in v2.2.0 and configurations using RDOQ should be around 1-3% faster with the AVX2 optimizations
Full Changelog: v2.2.0...v2.3.0
Contributors
@farindk
@PeterDaveHello
@matoro
@barracuda156
farindk, PeterDaveHello, and 2 other contributors
Assets
7
v2.2.0
Jan 4, 2023
@Arizer Arizer
v2.2.0
37a0404
v2.2.0
uvg266
We now also have a VVC encoder called uvg266, which is available at github/uvg266. The majority of future development will go towards uvg266 but do not consider Kvazaar to be abandoned!
Features
Updated Region of Interest (ROI) functionality to allow separate ROI map for each frame
Improve inter search
Update cabac context during search to improve the accuracy of bit cost estimation
Move intra chroma search option from --rd 3 to its own option --(no-)intra-chroma-search and fast bipred to --(no-)fast-bipred
Change maximum rd level to 4, where 3 performs more rd search for inter and 4 performs full intra search
Add --(no-)combine-intra-cus for controlling whether the larger intra blocks are tried even when search at current depth is disabled
Add --force-inter for debugging purposes to force all PUs in inter slices to use best inter mode
Optimizations
AVX2 implementations of bidirectional blending
Fixes
Make sure the dpb is more than max_num_reorder_pics 899c672
Compute proper count of buffered frames for vps and sps. Use common function d4880be
Fix some strategy function pointer signatures a400504
External contributors
build: fix automake warning by @bradh in #335
cli: add missing newlines in usage by @bradh in #336
refactor SEI by @bradh in #341
cli: minor api doc fix by @bradh in #342
add sudo ldconfig by @binbinzhm in #345
Enable -mpopcnt and -mlzcnt on AVX2 by @klondi in #301
New Contributors
@bradh made their first contribution in #335
@binbinzhm made their first contribution in #345
@klondi made their first contribution in #301
Performance
BD-Bitrate
Average BD-Bitrate compared with v2.1:
class0-uf1-sf2-vf3-fr4-f5-m6-s7-sr8-vs
hevc-A0.4 %0.7 %0.0 %-0.1 %0.0 %-1.1 %-0.8 %0.2 %-5.1 %
hevc-B0.3 %0.4 %-0.3 %-0.6 %-0.4 %-1.7 %-1.2 %0.1 %-7.1 %
hevc-C0.5 %1.1 %0.7 %0.5 %0.2 %-0.8 %-0.4 %0.4 %-5.5 %
hevc-D0.4 %1.5 %1.0 %0.6 %0.7 %-0.3 %-0.1 %0.4 %-6.6 %
hevc-E-2.1 %-1.7 %-2.2 %-2.5 %-2.5 %-1.4 %-1.1 %-1.1 %-5.4 %
hevc-F-0.1 %0.2 %-0.2 %-0.2 %-0.3 %-0.6 %-0.4 %0.1 %-3.1 %
total0.0 %0.4 %-0.1 %-0.3 %-0.3 %-1.0 %-0.7 %0.0 %-5.6 %
Speedup
Average speedup compared with v2.1 on an Intel Xeon W-2145 (8-core) machine:
class0-uf1-sf2-vf3-fr4-f5-m6-s7-sr8-vs
hevc-A1.09x1.10x1.12x1.14x1.15x1.08x1.04x1.10x0.68x
hevc-B1.10x1.09x1.15x1.15x1.15x1.09x1.07x1.14x0.66x
hevc-C1.11x1.06x1.11x1.14x1.14x1.07x1.08x1.03x0.75x
hevc-D1.08x1.08x1.13x1.13x1.14x1.08x1.08x1.06x0.71x
hevc-E1.07x1.08x1.11x1.14x1.14x1.08x1.10x1.12x0.62x
hevc-F1.10x1.05x1.07x1.09x1.08x1.05x1.05x1.02x0.67x
total1.09x1.08x1.12x1.13x1.13x1.08x1.07x1.08x0.68x
Full Changelog: v2.1.0...v2.2.0
Contributors
@bradh
@klondi
@binbinzhm
bradh, klondi, and binbinzhm
Assets
7
1 person reacted
v2.1.0
Oct 13, 2021
@Arizer Arizer
v2.1.0
cc22233
v2.1.0
Kvazaar 2.1 has been released!
Important update on the license
With this release, the license was changed from LGPL2.1 to 3-Clause BSD, allowing more liberties in using Kvazaar.
Features
Option to use a custom table for fast bitrate estimation weights (--fast-coeff-table <file>)
Tools to create new weight sets for fast bitrate estimation (--fast-rd-sampling, --fastrd-accuracy-check, --fastrd-outdir), documented in rdcost-weight-tool/README.txt
Added support for Y4M input in addition to YUV (Autodetected, manually enable using --input-file-format=y4m)
Allow writing out block statistics for debugging (--stats-file-prefix)
Optimizations
New AVX2 implementations for interpolation filters
Fixes
DTS offset was incorrect at the beginning of the sequence when using GOP (7918628
)
Added VPS information about reordering and buffering, fixes VLC playback (b68625b)
Removed pthread_exit() on mingw to fix media-autobuild suite (9a65617)
Renamed truncate function to not overlap with POSIX one, fixed FreeBSD build (1fa69c7)
Assets
7
v2.0.0
Apr 22, 2020
@Arizer Arizer
v2.0.0
9753820
v2.0.0
Kvazaar 2.0 has been released!
Since 1.3, the encoder has received such improvements and fixes that make this one of our most significant releases so far. It is only fitting to call this version 2.0.
Here are some of the more interesting changes in this release:
Important for MinGW users
AVX2 optimizations are no longer enabled for MinGW GCC due to stack alignment issues.
Use Clang for AVX2 support and therefore better performance.
Highlights
Updated presets
Updated GOP definitions using QP offset model.
There is now even longer hierarchical GOP --gop=16
Much faster and improved bipred
Alternative and better rate control algorithm, optimal bit allocation (--rc-algorithm oba)
Variance adaptive quantization (--vaq)
Features
Option to set QP offset for intra frames (--intra-qp-offset, automatical by default)
Zero-coeff-rdo is now configurable (--zero-coeff-rdo)
Optional intra frame analysis for rate control (--intra-bits)
Optional machine learning based depth constraints for intra search (--ml-pu-depth-intra)
PU depths are now separately configurable for each GOP layer
User Interface
Report bitrate and some kind of (cumulative) average QP
Optimizations:
More AVX2 opimizations for SAO
More AVX2 opimizations for transforms
More AVX2 opimizations for intra prediction
AVX2 strategy for variance calculation
...and several other improvements and fixes
BD-Bitrate
Average BD-Bitrate compared with v1.3:
class0-uf1-sf2-vf3-fr4-f5-m6-s7-sr8-vs
hevc-A-20.2 %-21.4 %-28.8 %-24.8 %-21.4 %-23.5 %-19.1 %-11.3 %-15.0 %
hevc-B-35.1 %-34.5 %-34.7 %-31.8 %-28.6 %-29.5 %-21.8 %-11.4 %-16.2 %
hevc-C-21.0 %-23.6 %-31.3 %-27.7 %-22.4 %-23.5 %-19.8 %-12.9 %-18.0 %
hevc-D-22.5 %-26.6 %-37.4 %-33.2 %-26.6 %-25.3 %-18.3 %-10.8 %-15.1 %
hevc-E-35.9 %-34.9 %-30.9 %-29.8 %-28.0 %-30.4 %-25.7 %-19.0 %-20.2 %
hevc-F-18.6 %-17.7 %-21.3 %-19.9 %-17.5 %-15.2 %-17.6 %-26.8 %-37.0 %
Total-26.0 %-26.9 %-31.1 %-28.2 %-24.4 %-24.6 %-20.3 %-15.4 %-20.6 %
Speedup
Average speedup compared with v1.3 on an AMD Ryzen 7 1700X machine:
class0-uf1-sf2-vf3-fr4-f5-m6-s7-sr8-vs
hevc-A0.90x0.75x0.80x0.78x0.93x1.11x1.21x1.23x0.95x
hevc-B0.96x0.81x0.83x0.82x0.97x1.15x1.26x1.29x0.95x
hevc-C0.94x0.78x0.73x0.70x0.83x1.12x1.22x1.26x0.86x
hevc-D1.02x0.83x0.78x0.76x0.90x1.16x1.24x1.28x0.93x
hevc-E0.95x0.84x0.91x0.89x1.06x1.45x1.56x1.42x1.16x
hevc-F0.96x0.85x0.84x0.84x0.94x1.17x1.29x1.25x1.00x
Total0.96x0.81x0.81x0.80x0.93x1.18x1.29x1.29x0.97x
Assets
7
v1.3.0
Jul 9, 2019
@Arizer Arizer
v1.3.0
5db3a78
v1.3.0
Time has finally come for the long overdue release v1.3 of Kvazaar!
Since it has been such a long time after our previous release, many many new features, fixes, and optimizations have been introduced and the coding efficiency is on a whole new level.
Binaries for Windows will be added starting from this release.
Pthreads is no longer needed to build and run Kvazaar on Windows. It has been replaced by our custom ThreadWrapper so Kvazaar is able to use the new c++ standard threads. ThreadWrapper is also separately available on repository https://github.com/ultravideo/ThreadWrapper and released under ISC lisence. It is not complete yet, so contributions are welcome.
Performance figures and more up-to-date release notes will be added in the following days.
Some CI tests are failing at the moment, but there should not be any critical issues.
Edit (2.5.2020):
Here are some of the previously missing missing release notes:
Features
Option --fast-residual-cost to gain speedup with less accurate mode decisions
Option --(no-)open-gop to choose between open and closed GOP
Option --set-qp-in-cu to move QP signalling into CU level for very specific use cases
Option --scaling-list to enable choose enable and choose scaling lists
Option --max-merge to set the maximum amount of merge candidates
Option --early-skip to speed up coding at the cost of worse results
Optimizations
Another version of interplation filters and fractional pixel motion estimation
AVX2 optimized sign bit hiding
AVX2/BMI2 optimized coefficient coding
AVX2 blending for biprediction
Improvements and AVX2 code for certain SAD functions
Building
ASM: marked stack non-executable
The old notes:
Features
Changed --rd=2 to use SSD metric for CU mode decision (662430d)
Changed inter search to check the cost of flushing residual to zero (75a8700)
Changed rectangular and asymmetric blocks to use a transform split (774c666)
Added diamond search ME algorithm (4e13608)
Enabled low delay B GOP structure with --bipred --gop=lp-g4d3t1 (7155dd0)
Added termination of intra search at zero residual with --intra-rdo-et (4fb1c16)
Optimization
Made TZ search faster and slightly better (c136044)
Optimized bi-prediction (69756e2)
Fixes
Fixed transform skip with rectangular inter blocks (fb462b2)
Fixed accidental inter search for 4x4 blocks (649113a)
User Interface
Changed options for all preset levels (f033ad0)
Added an option for limiting the number of steps in motion estimation with --me-steps (39ed368)
Added --me=dia (4e13608)
Added --level, --force-level and --high-tier for setting bitstream level and tier (bac0745)
Building
Fixed issue with struct timespec redefinition with Visual Studio 2015 and later (713e694)
Fixed building .asm files in Visual Studio 2017 (6be8195)
Fixed compatibility with crypto++ 6.0 (4b24cd0)
Added support for crypto++ with the name libcryptopp (411276d)
Dockerfile base image was updated to Ubuntu 18.04 (8380b6c)
Enabled -Wextra by default (ff17e0b)
Refactoring
Inter motion vector cost functions (c73cce3)
Dockerfile (0164291)
BD-Bitrate
Average BD-Bitrate compared with v1.2:
Class0-uf1-sf2-vf3-fr4-f5-m6-s7-sr8-vs
hevc-A-18.8 %-17.5 %-1.7 %-6.2 %-2.1 %-6.1 %-8.7 %-19.1 %-19.2 %
hevc-B-21.3 %-20.9 %-4.6 %-5.7 %-2.9 %-6.6 %-11.8 %-26.4 %-23.9 %
hevc-C-26.6 %-24.9 %-2.4 %-8.3 %-3.7 %-11.9 %-11.0 %-26.1 %-21.0 %
hevc-D-33.3 %-31.1 %-1.8 %-11.5 %-7.5 %-16.5 %-16.2 %-28.9 %-23.6 %
hevc-E-26.3 %-25.3 %-20.4 %-15.4 %-13.8 %-15.7 %-21.3 %-26.3 %-25.9 %
hevc-F-9.2 %-8.4 %-5.2 %-4.9 %-3.0 %-20.8 %-17.3 %0.2 %18.8 %
Total-22.7 %-21.5 %-5.7 %-8.4 %-5.3 %-13.2 %-14.4 %-21.3 %-15.4 %
Speedup
Average speedup compared with v1.2 on an Intel Xeon E5-2620 v4 machine:
class0-uf1-sf2-vf3-fr4-f5-m6-s7-sr8-vs
hevc-Ax0.88x0.91x1.02x1.19x1.37x0.76x0.93x0.58x0.36
hevc-Bx0.90x0.92x1.08x1.21x1.40x0.81x0.99x0.62x0.38
hevc-Cx0.87x0.88x0.96x1.11x1.24x0.59x0.72x0.40x0.26
hevc-Dx0.92x0.97x1.03x1.23x1.34x0.65x0.74x0.38x0.27
hevc-Ex0.97x0.94x1.08x1.15x1.34x0.86x1.05x0.74x0.54
hevc-Fx0.81x0.91x1.01x1.09x1.30x0.78x0.88x0.49x0.35
Totalx0.89x0.92x1.03x1.17x1.33x0.74x0.88x0.53x0.35
Assets
7
v1.2.0
Nov 17, 2017
@ari-koivula ari-koivula
v1.2.0
cf85d52
v1.2.0
We are happy to release Kvazaar version 1.2. Since the last version, Kvazaar has obtained significant speedups at all presets and the compression efficiency has improved for the fastest presets. Please find the complete list of changes below.
Features
Intra prediction mode encryption with --crypto=intra_pred_modes (2b8ce5e)
Adaptive QP for 360° video with --erp-aqp (26adef4)
New selection algorithm for --owf=auto and --threads=auto (8c4a347)
Added an option to set the encryption key using --key (2e13091)
Added an option to limit SAO to band offset or edge offset only with --sao=band and --sao=edge (8674c0f)
Optimization
Reduced number of intra modes checked when using --rd=2 (2cad317)
Reduced inter-frame CTU dependencies caused by SAO (050e90d)
Changed to a faster calculation for coefficient costs when using --rd=0 (1ead9c0)
Fixes
Fixed long motion vectors not getting clipped (#158, 85e2a40)
Fixed order of pictures in reconstruction debug output when --gop=8 is used (#101, aae141f)
Fixed a use-after-free when encoding very few frames with --gop=8 (#161, 2991962)
Fixed a crash when video size is not a multiple of the smallest CU size (2f2405d)
Fixed invalid bitstream when QP is too large (382636d)
Fixed a race condition causing a deadlock (5f8e17d)
Fixed a memory leak in encryption (8654b48)
Fixed I-frames not being IRAP frames when using GOP (00c9f52, 841597e)
Fixed computing inter and intra costs with different metrics (afc13f1)
Fixed reliance on undefined behavior (b41f0fa, 924cf85)
Fixed --mv-constraint=frametilemargin constraining motion vectors too much (409d211)
Fixed using --bipred with --tmvp (#160, 9974380)
User Interface
Changed type of kvz_config.roi.dqps from uint8_t* to int8_t. Delta QP values for --roi may now be negative. (79cb3a2)
Changed PSNR display format (20d6444)
Building
Default to no -Werror. Run configure with --enable-werror to enable it. (033bc6b)
make check now runs valgrind tests that used to only run on Travis. Programs ffmpeg, valgrind and TAppDecoderStatic should be found from $PATH (6bbe5e1)
Refactoring
Removed duplicate code in inter MVP and merge candidate selection (4fb0783)
Removed duplicate code in intra reconstruction for luma and chroma (e944416)
Changed functions for writing the CU tree bitstream to use luma pixel coordinates (610c91b, f5eef7f)
Removed duplicate code in functions for writing intra CU bitstream with and without encryption (525a518)
Removed duplicate code in helper functions in search.c (2c73476)
Gathered function parameters for inter search functions into a single struct (2fa3d82)
BD-Bitrate
Average BD-Bitrate compared with v1.1:
Class0-uf1-sf2-vf3-fr4-f5-m6-s7-sr8-vs
hevc-A-15.71 %-6.68 %-4.66 %-0.89 %-1.11 %-0.54 %+0.04 %-0.02 %+0.32 %
hevc-B-19.04 %-8.15 %-6.92 %-1.26 %-1.48 %-0.65 %-0.33 %-0.33 %-0.07 %
hevc-C-20.39 %-8.54 %-5.01 %-0.55 %-0.72 %-0.44 %+0.03 %-0.00 %+0.23 %
hevc-D-13.24 %-5.15 %-2.54 %-0.33 %-0.51 %-0.32 %-0.10 %-0.04 %+0.13 %
hevc-E-4.37 %-3.31 %-1.90 %-0.52 %-1.10 %-0.68 %-0.74 %-0.86 %-0.78 %
hevc-F-12.42 %-6.15 %-5.25 %+0.04 %+0.24 %+0.25 %+0.32 %+0.70 %+0.90 %
Total-14.80 %-6.59 %-4.68 %-0.60 %-0.78 %-0.39 %-0.13 %-0.08 %+0.14 %
Speedup
Average speedup compared with v1.1 on an Intel Core i7-4770 machine:
Class0-uf1-sf2-vf3-fr4-f5-m6-s7-sr8-vs
hevc-Ax1.07x1.06x1.10x1.10x1.09x1.11x1.10x1.11x1.10
hevc-Bx1.06x1.07x1.09x1.11x1.09x1.13x1.12x1.13x1.14
hevc-Cx1.22x1.27x1.32x1.35x1.33x1.37x1.39x1.42x1.41
hevc-Dx1.34x1.58x1.64x1.60x1.58x1.54x1.55x1.57x1.54
hevc-Ex1.20x1.17x1.16x1.18x1.16x1.17x1.16x1.20x1.19
hevc-Fx1.25x1.20x1.20x1.23x1.20x1.24x1.24x1.27x1.27
Totalx1.19x1.22x1.24x1.26x1.24x1.26x1.26x1.28x1.28
Assets
5
v1.1.0
Feb 16, 2017
@ari-koivula ari-koivula
v1.1.0
7369f25
v1.1.0
I think there are enough new features to call this v1.1.0.
Average BD bitrate (QP 17, 22, 27, 32) v1.1.0 vs v1.0.0
Class0-uf1-sf2-vf3-fr4-f5-m6-s7-sr8-vs
A-1.9%-1.5%-1.2%-1.0%-0.7%-0.7%-1.1%-1.1%-1.3%
B-2.2%-1.3%-1.4%-0.8%-0.5%-0.6%-0.9%-0.8%-1.0%
C-1.3%-1.1%-1.0%-0.9%-0.6%-0.6%-0.6%-0.6%-0.8%
D-1.1%-0.9%-0.7%-0.7%-0.6%-0.5%-0.1%-0.2%-0.4%
E-2.5%-1.5%-0.9%-0.7%-0.3%-0.3%-0.5%-0.4%-0.4%
F-1.6%-0.7%-0.9%-0.8%-0.5%-0.4%-0.7%-0.7%-0.7%
All-1.7%-1.2%-1.0%-0.8%-0.5%-0.5%-0.6%-0.6%-0.8%
Average speedup (QP 17, 22, 27, 32) v1.1.0 vs v1.0.0
Class0-uf1-sf2-vf3-fr4-f5-m6-s7-sr8-vs
A1.03x1.02x1.01x1.01x1.01x1.02x1.07x1.09x1.16x
B1.03x1.01x1.02x1.01x1.01x1.01x1.06x1.06x1.13x
C1.03x1.02x1.01x1.01x1.01x1.01x1.07x1.07x1.16x
D1.07x1.05x1.03x1.03x1.02x1.02x1.07x1.09x1.17x
E0.99x0.97x0.98x0.99x0.99x0.99x1.00x1.02x1.05x
F1.02x1.01x1.01x1.01x1.01x1.01x1.08x1.09x1.17x
All1.03x1.02x1.01x1.01x1.01x1.01x1.06x1.07x1.14x
Paramaters: --threads=4 --owf=1 -p64
Features
Bitrate control now works at LCU level, giving more consistent results. (2318bd7)
Added --roi parameter for LCU level delta-QP control. (4a0121a)
Added --slices parameter for encapsulating tiles and WPP-rows into slice NAL's instead of using bitstream offsets. (1e6463c)
Temporal motion vector prediction now works with B-frames. (d892be5)
Optimization
Added AVX2 version of SSD. (778e46d)
Optimized intra reference building. (c31207e)
Optimized bitstream writes. (a9e45ef)
Optimized CU-split decision. (2c069a3)
Fix main-thread busy-looping on Linux. (a5a925f)
Avoid initializing memory needlessly during RDOQ. (acd12cb, b021d22)
Fixes
Pass DTS and PTS timestamps correctly through the API. (d18de19)
Fixed bug with subpixel motion estimation within tiles. (2c005cd)
Improved 10-bit RD-performance. (70a52f0)
Fixed for stupendously large bitstreams when --mv-constraint was used with --subme. (937a764)
Fixed bug with --smp and --amp. (46c9a48)
Fix problem with --bipred. (1e6463c)
Fixed hang with threading on OSX. (d893474)
Fix crash when frame is less than 65 pixels high and WPP is used. (b8e3513)
User Interface
Disabled WPP with tiles enabled. (cb6672b)
Improved --help. (5bf7454, 78a28e0)
Made it possible to disable the gop-structure that was enabled by default in v.1.0.0. (deb63f7)
Have --threads=auto enable threading instead of disabling it. (db5e750)
Give errors on failures and handle them better. (97863cd, 6a178de)
Use reference picture number of medium preset by default. (7ff33e1)
Building
Include optimizations on 32-bit. (1dcc993)
Added appveyor CI tests for MSYS2. (e269b86)
Add pkg-config macros, so pkg-config doesn't need to be installed anymore. (2d7daa1)
Travis CI OSX tests work again. (c32f5fa)
Refactoring
Refactored deblocking and sign hiding. (7ec5f78)
Removed Exp-Golomb lookup table. (ed3bd89)
Copy kvz_config to encoder_control_t and remove duplicate fields. (e78a8df)
Assets
5
v1.0.0
Oct 4, 2016
@ari-koivula ari-koivula
v1.0.0
e7cdd47
v1.0.0
It's been 9 months since last release. Now that the encoder just got 10x faster (on veryslow), and quite a bit faster and better on every other preset as well, I think it's time for a major verson bump.
Average BD bitrate (QP 17, 22, 27, 32) v1.0.0 vs v0.8.3
Class0-uf1-sf2-vf3-fr4-f5-m6-s7-sr8-vs
A-16.4%-26.9%-27.5%-31.0%-11.2%-11.9%-11.3%-6.7%-4.8%
B-16.2%-33.7%-31.7%-37.6%-11.6%-14.8%-15.7%-9.1%-6.3%
C-7.0%-17.6%-28.0%-31.2%-8.3%-9.0%-11.3%-7.1%-8.1%
D-3.7%-12.3%-29.2%-30.3%-5.4%-5.9%-11.5%-8.3%-9.9%
E-28.4%-42.6%-33.5%-39.4%-22.6%-28.5%-20.3%-7.0%-0.7%
F-6.1%-11.3%-12.8%-16.5%-10.1%-2.1%2.3%10.8%6.4%
|
|All|-13.0%|-24.1%|-27.1%|-31.0%|-11.5%|-12.0%|-11.3%| -4.6%| -3.9%|
Average speedup (QP 17, 22, 27, 32) v1.0.0 vs v0.8.3
Class0-uf1-sf2-vf3-fr4-f5-m6-s7-sr8-vs
A1.61x1.91x1.89x1.37x2.69x3.33x4.79x7.32x11.06x
B1.65x1.98x1.96x1.46x2.67x3.36x4.79x8.15x13.89x
C1.76x1.97x1.98x1.45x2.52x2.97x4.87x9.32x15.77x
D2.09x1.87x1.81x1.32x1.97x2.36x5.13x8.78x12.65x
E1.91x1.96x1.75x1.40x3.00x3.70x4.87x6.06x7.56x
F1.84x1.83x1.74x1.41x2.86x2.98x4.60x8.18x13.58x
|
|All|1.81x|1.92x|1.86x|1.40x|2.62x|3.12x|4.84x|7.97x|12.42x|
Paramaeters: --threads=4 --owf=1 --wpp -p64
New Features
--version
--help
--loop-input
--mv-constraint to constrain motion vectors
--tiles=2x2 as an alternative syntax for uniform tiles
--hash=md5
Print information about what SIMD optimizations are in use
--mv=full8 --mv=full16 --mv=full32 --mv=full64
--cu-split-termination=zero/off
--crypto for selective encryption of bitstream (for OpenHEVC)
--me-early-termination=sensitive/on/off for early termination of motion vector search
Added 4x8 SMP and 4x12 AMP motion partitions
--subme=0/1/2/3/4 for control over complexity of fractional pixel motion prediction
--lossless for lossless coding
Monochrome coding
--input-format=420/400
--input-bitdepth=8/10
--tmpv for temporal motion vector predictor
--rdoq-skip for not using rdoq for situations where it's unlikely to improve BDRate
Modified --gop=lp-g4d3r1t1 syntax to not take the reference frames as a parameter, it's now --gop=lp-g4d3t1.
Enable WPP and multithreading by default, with detection for number of cores
Update all presets to ratedistortion-complexity optimized versions. These are based on a search of all (~ish) possible encoding parameters and bring a huge boost to both speed and BDRate when encoding with the presets (10x speed for veryslow, ~1.1x-4x for others, up to 30% improved BDRate for some presets).
Set default options to match medium with intra period of 64, QP 22 and --gop=lp-g4d3t1
--implicit-rdpcm RExt feature
Optimizations
AVX2 version for Sample Adaptive Offset (SAO)
Optimized memory copying
AVX2 versions of filters for fractional pixel motion estimation
AVX2 version for half pixel chroma sampling for SMP/AMP
AVX2 versions for calculating two or four SATD values at once for small blocks
Rewrote AVX2 version of fractional pixel motion compensation
Rewrote motion vector cost calculation. It only got slightly faster, but BDRate improved a bunch due to the new implementation being more correct.
Made AVX2 SAD use SSE4.1 for cases where there isn't an AVX2 implementation, speeding up SMP/AMP.
Bugfixes
Fixed a bug in rate control where an int overflowed after coding 2^31 bits (2Gb)
Fixed non-determinism intiles
Fixed chroma reconstruction bug in tiles
Fixed a bug with calculating the number of bits used for intra mode on 4x4 CUs
Stopped checking zero motion vector multiple times in motion compensation
Fixed possible segfault in motion compensation
Fixed a race condition with OWF and SMP/AMP
Gave pthread_cond_timedwait time in correctly, such that main thread now sleeps instead of busylooping when it has nothing to do
Fixed rate control with lp-gop
Fixed full search not taking temporal motion vector into account
Allow non-gop-length intra period for lp-gop
Code / Building / Testing
Moved SAO to it's own file
Removed a ton of unnecessary includes
Updated autotools ax_pthread
Added build test for OS-X for Travis
Made tests check for bitstream correctness
Refactored some of the copypasta in motion vector search starting point selection
Refactored the cu_info_t datastructures to hold information at a 4x4 resolution needed for AMP and SMP
Changed cu_info_t to use bitfields to negate the effect of increasing the cu_info_t array by a factor of 4
Moved bitstream generation from encoderstate.c to encode_coding_tree.c
Renamed encoder_state_t.global to frame, which makes sense since it hold frame level data, not global data
Rewrote integer vector inter prediction, because it was so bad
Refactored init_lcu_t
Added more tests for inter SAD
Added speed tests for dual intra SAD functions
Added more realistic speed tests for inter SAD
Other
Added a manpage
Added scripts for updating manpage and README based on --usage.
Added a Dockerfile. Just because.
Added commit date to --version
Features
There are no major new features, but several fixes, most notably to 10 bit encoding and cost calculation for smp and amp blocks. Due to the fixes to amp cost calculation, amp is now enabled on veryslow preset.
Impact of fixes on the old veryslow preset
SequencesBD-BR (PSNR)BD-BR (SSIM)Speed
hevc-A-1.2 %-1.4 %0.96×
hevc-B-1.4 %-1.6 %0.97×
hevc-C-1.2 %-1.4 %0.97×
hevc-D-1.3 %-1.6 %0.98×
hevc-E-0.9 %-1.0 %1.00×
hevc-F-1.1 %-1.4 %0.98×
Overall-1.2 %-1.4 %0.98×
Veryslow of v2.3.1 vs v2.3.2
SequencesBD-BR (PSNR)BD-BR (SSIM)Speed
hevc-A-3.1 %-3.5 %0.69×
hevc-B-3.0 %-3.2 %0.72×
hevc-C-2.9 %-3.3 %0.78×
hevc-D-2.9 %-3.3 %0.82×
hevc-E-2.3 %-2.1 %0.83×
hevc-F-2.4 %-2.8 %0.79×
Overall-2.7 %-3.0 %0.77×
To other presets the impact of fixes is smaller
Fixes
Several fixes to 10 bit encoding
Fix SATD calculation 36f7752
Ensure proper stack size 1eeccb3
Fix typing for threadwrapper a7aeb23
Separate .pdb files for exe and library ccc643c
Fix y4m reading 4aeeba7 b8d9185
Update minimum CMake version 3393d56
Fix --no-early-skip d1e11d8
Fix lossless incorrectly selecting skip d1e11d8
Rate control improvements 526c8db 999c512
Fix bit cost calculation for tr splits and smp 6957cea
Update the default configuration to match the medium preset 3eed14d
External contributions
add missing files in distribution for compilation with cmake by @vtorri in #402
encmain.c: guard WINVER and _WIN32_WINNT macros by @vtorri in #405
ax_pthread/clang: move -pthread to LIBS by @1480c1 in #407
fix ios build by @trittsv in #416
fix android build by @trittsv in #415
Fix Windows ARM64 builds when using MSVC by @anthony-linaro in #419
Fix emscripten build by @meowtec in #422
Add BSDs to exclusion list for compiler flag with cmake by @rhelmot in #426
Avoid double free of roi.file_path by @bart-kroon in #428
Fix passing too many arguments to "init_test_strategies". by @fancycode in #440
V2.3.1
Features
New AVX2 optimizations for intra angular predictions, faster and gets around a code generation issue with MSVC > 19.36
Fixes
Several fixes to CMakeLists.txt
fix unaligned access on array_checksum_generic8 c6f2ba4
fix preset log while enable-logging to false 7424474
Include CMakeLists.txt in dist 3b1bcb6
External contributions
Fix typo in error message. by @fancycode in #386
Minor cmake fixes by @lgbaldoni and @kmilos in #385
Ignore "*get_pc_thunk.*" symbols in exported symbols test by @matoro in #392
Fixed issue #394 - missing _mm256_storeu2_m128i macro by @supersjgk in #395
New Contributors
@fancycode made their first contribution in #386
@lgbaldoni made their first contribution in #385
@supersjgk made their first contribution in #395
Performance
With the new AVX2 intra prediction the encoder is 1-5% faster, depending on settings
Full Changelog: v2.3.0...v2.3.1
Contributors
@fancycode
@lgbaldoni
@kmilos
@matoro
@supersjgk
fancycode, lgbaldoni, and 3 other contributors
Assets
7
3 people reacted
V2.3.0
Jan 17, 2024
@Jovasa Jovasa
v2.3.0
e8be7ac
V2.3.0
Features
--(no-)enable-logging to enable/disable logging of normal encoder perfomance into stderr, errors are still outputted to stderr.
AVX2 optimisations for finding last non zero coefficient in RDOQ
Remove YASM to make compilation with visual studio easier
Experimental support for CMake, in the future we would like to get rid of automake and visual studio so if there are any issues with the CMakeLists.txt please report them
Fixes
Fix a bug when requesting encoder_headers before any frame has been pushed in aaae5b0
Fix a problem with win+gcc (mingw, msys, cygwin) causing some optimized functions to segfault 589ed47
Fix GCC detection for automake 49dc5fc 8523c96
External contributions
add config option to turn off logging output (#356) by @farindk in #357
Update Dockerfile base image to Ubuntu 20.04 by @PeterDaveHello in #358
threads.h: fix for older macOS builds by @barracuda156 in #373
Don't export MD5 byteReverse symbol on big-endian by @matoro in #377
New Contributors
@farindk made their first contribution in #357
@barracuda156 made their first contribution in #373
@matoro made their first contribution in #377
Performance
The RD performance should be exactly the same as in v2.2.0 and configurations using RDOQ should be around 1-3% faster with the AVX2 optimizations
Full Changelog: v2.2.0...v2.3.0
Contributors
@farindk
@PeterDaveHello
@matoro
@barracuda156
farindk, PeterDaveHello, and 2 other contributors
Assets
7
v2.2.0
Jan 4, 2023
@Arizer Arizer
v2.2.0
37a0404
v2.2.0
uvg266
We now also have a VVC encoder called uvg266, which is available at github/uvg266. The majority of future development will go towards uvg266 but do not consider Kvazaar to be abandoned!
Features
Updated Region of Interest (ROI) functionality to allow separate ROI map for each frame
Improve inter search
Update cabac context during search to improve the accuracy of bit cost estimation
Move intra chroma search option from --rd 3 to its own option --(no-)intra-chroma-search and fast bipred to --(no-)fast-bipred
Change maximum rd level to 4, where 3 performs more rd search for inter and 4 performs full intra search
Add --(no-)combine-intra-cus for controlling whether the larger intra blocks are tried even when search at current depth is disabled
Add --force-inter for debugging purposes to force all PUs in inter slices to use best inter mode
Optimizations
AVX2 implementations of bidirectional blending
Fixes
Make sure the dpb is more than max_num_reorder_pics 899c672
Compute proper count of buffered frames for vps and sps. Use common function d4880be
Fix some strategy function pointer signatures a400504
External contributors
build: fix automake warning by @bradh in #335
cli: add missing newlines in usage by @bradh in #336
refactor SEI by @bradh in #341
cli: minor api doc fix by @bradh in #342
add sudo ldconfig by @binbinzhm in #345
Enable -mpopcnt and -mlzcnt on AVX2 by @klondi in #301
New Contributors
@bradh made their first contribution in #335
@binbinzhm made their first contribution in #345
@klondi made their first contribution in #301
Performance
BD-Bitrate
Average BD-Bitrate compared with v2.1:
class0-uf1-sf2-vf3-fr4-f5-m6-s7-sr8-vs
hevc-A0.4 %0.7 %0.0 %-0.1 %0.0 %-1.1 %-0.8 %0.2 %-5.1 %
hevc-B0.3 %0.4 %-0.3 %-0.6 %-0.4 %-1.7 %-1.2 %0.1 %-7.1 %
hevc-C0.5 %1.1 %0.7 %0.5 %0.2 %-0.8 %-0.4 %0.4 %-5.5 %
hevc-D0.4 %1.5 %1.0 %0.6 %0.7 %-0.3 %-0.1 %0.4 %-6.6 %
hevc-E-2.1 %-1.7 %-2.2 %-2.5 %-2.5 %-1.4 %-1.1 %-1.1 %-5.4 %
hevc-F-0.1 %0.2 %-0.2 %-0.2 %-0.3 %-0.6 %-0.4 %0.1 %-3.1 %
total0.0 %0.4 %-0.1 %-0.3 %-0.3 %-1.0 %-0.7 %0.0 %-5.6 %
Speedup
Average speedup compared with v2.1 on an Intel Xeon W-2145 (8-core) machine:
class0-uf1-sf2-vf3-fr4-f5-m6-s7-sr8-vs
hevc-A1.09x1.10x1.12x1.14x1.15x1.08x1.04x1.10x0.68x
hevc-B1.10x1.09x1.15x1.15x1.15x1.09x1.07x1.14x0.66x
hevc-C1.11x1.06x1.11x1.14x1.14x1.07x1.08x1.03x0.75x
hevc-D1.08x1.08x1.13x1.13x1.14x1.08x1.08x1.06x0.71x
hevc-E1.07x1.08x1.11x1.14x1.14x1.08x1.10x1.12x0.62x
hevc-F1.10x1.05x1.07x1.09x1.08x1.05x1.05x1.02x0.67x
total1.09x1.08x1.12x1.13x1.13x1.08x1.07x1.08x0.68x
Full Changelog: v2.1.0...v2.2.0
Contributors
@bradh
@klondi
@binbinzhm
bradh, klondi, and binbinzhm
Assets
7
1 person reacted
v2.1.0
Oct 13, 2021
@Arizer Arizer
v2.1.0
cc22233
v2.1.0
Kvazaar 2.1 has been released!
Important update on the license
With this release, the license was changed from LGPL2.1 to 3-Clause BSD, allowing more liberties in using Kvazaar.
Features
Option to use a custom table for fast bitrate estimation weights (--fast-coeff-table <file>)
Tools to create new weight sets for fast bitrate estimation (--fast-rd-sampling, --fastrd-accuracy-check, --fastrd-outdir), documented in rdcost-weight-tool/README.txt
Added support for Y4M input in addition to YUV (Autodetected, manually enable using --input-file-format=y4m)
Allow writing out block statistics for debugging (--stats-file-prefix)
Optimizations
New AVX2 implementations for interpolation filters
Fixes
DTS offset was incorrect at the beginning of the sequence when using GOP (7918628
)
Added VPS information about reordering and buffering, fixes VLC playback (b68625b)
Removed pthread_exit() on mingw to fix media-autobuild suite (9a65617)
Renamed truncate function to not overlap with POSIX one, fixed FreeBSD build (1fa69c7)
Assets
7
v2.0.0
Apr 22, 2020
@Arizer Arizer
v2.0.0
9753820
v2.0.0
Kvazaar 2.0 has been released!
Since 1.3, the encoder has received such improvements and fixes that make this one of our most significant releases so far. It is only fitting to call this version 2.0.
Here are some of the more interesting changes in this release:
Important for MinGW users
AVX2 optimizations are no longer enabled for MinGW GCC due to stack alignment issues.
Use Clang for AVX2 support and therefore better performance.
Highlights
Updated presets
Updated GOP definitions using QP offset model.
There is now even longer hierarchical GOP --gop=16
Much faster and improved bipred
Alternative and better rate control algorithm, optimal bit allocation (--rc-algorithm oba)
Variance adaptive quantization (--vaq)
Features
Option to set QP offset for intra frames (--intra-qp-offset, automatical by default)
Zero-coeff-rdo is now configurable (--zero-coeff-rdo)
Optional intra frame analysis for rate control (--intra-bits)
Optional machine learning based depth constraints for intra search (--ml-pu-depth-intra)
PU depths are now separately configurable for each GOP layer
User Interface
Report bitrate and some kind of (cumulative) average QP
Optimizations:
More AVX2 opimizations for SAO
More AVX2 opimizations for transforms
More AVX2 opimizations for intra prediction
AVX2 strategy for variance calculation
...and several other improvements and fixes
BD-Bitrate
Average BD-Bitrate compared with v1.3:
class0-uf1-sf2-vf3-fr4-f5-m6-s7-sr8-vs
hevc-A-20.2 %-21.4 %-28.8 %-24.8 %-21.4 %-23.5 %-19.1 %-11.3 %-15.0 %
hevc-B-35.1 %-34.5 %-34.7 %-31.8 %-28.6 %-29.5 %-21.8 %-11.4 %-16.2 %
hevc-C-21.0 %-23.6 %-31.3 %-27.7 %-22.4 %-23.5 %-19.8 %-12.9 %-18.0 %
hevc-D-22.5 %-26.6 %-37.4 %-33.2 %-26.6 %-25.3 %-18.3 %-10.8 %-15.1 %
hevc-E-35.9 %-34.9 %-30.9 %-29.8 %-28.0 %-30.4 %-25.7 %-19.0 %-20.2 %
hevc-F-18.6 %-17.7 %-21.3 %-19.9 %-17.5 %-15.2 %-17.6 %-26.8 %-37.0 %
Total-26.0 %-26.9 %-31.1 %-28.2 %-24.4 %-24.6 %-20.3 %-15.4 %-20.6 %
Speedup
Average speedup compared with v1.3 on an AMD Ryzen 7 1700X machine:
class0-uf1-sf2-vf3-fr4-f5-m6-s7-sr8-vs
hevc-A0.90x0.75x0.80x0.78x0.93x1.11x1.21x1.23x0.95x
hevc-B0.96x0.81x0.83x0.82x0.97x1.15x1.26x1.29x0.95x
hevc-C0.94x0.78x0.73x0.70x0.83x1.12x1.22x1.26x0.86x
hevc-D1.02x0.83x0.78x0.76x0.90x1.16x1.24x1.28x0.93x
hevc-E0.95x0.84x0.91x0.89x1.06x1.45x1.56x1.42x1.16x
hevc-F0.96x0.85x0.84x0.84x0.94x1.17x1.29x1.25x1.00x
Total0.96x0.81x0.81x0.80x0.93x1.18x1.29x1.29x0.97x
Assets
7
v1.3.0
Jul 9, 2019
@Arizer Arizer
v1.3.0
5db3a78
v1.3.0
Time has finally come for the long overdue release v1.3 of Kvazaar!
Since it has been such a long time after our previous release, many many new features, fixes, and optimizations have been introduced and the coding efficiency is on a whole new level.
Binaries for Windows will be added starting from this release.
Pthreads is no longer needed to build and run Kvazaar on Windows. It has been replaced by our custom ThreadWrapper so Kvazaar is able to use the new c++ standard threads. ThreadWrapper is also separately available on repository https://github.com/ultravideo/ThreadWrapper and released under ISC lisence. It is not complete yet, so contributions are welcome.
Performance figures and more up-to-date release notes will be added in the following days.
Some CI tests are failing at the moment, but there should not be any critical issues.
Edit (2.5.2020):
Here are some of the previously missing missing release notes:
Features
Option --fast-residual-cost to gain speedup with less accurate mode decisions
Option --(no-)open-gop to choose between open and closed GOP
Option --set-qp-in-cu to move QP signalling into CU level for very specific use cases
Option --scaling-list to enable choose enable and choose scaling lists
Option --max-merge to set the maximum amount of merge candidates
Option --early-skip to speed up coding at the cost of worse results
Optimizations
Another version of interplation filters and fractional pixel motion estimation
AVX2 optimized sign bit hiding
AVX2/BMI2 optimized coefficient coding
AVX2 blending for biprediction
Improvements and AVX2 code for certain SAD functions
Building
ASM: marked stack non-executable
The old notes:
Features
Changed --rd=2 to use SSD metric for CU mode decision (662430d)
Changed inter search to check the cost of flushing residual to zero (75a8700)
Changed rectangular and asymmetric blocks to use a transform split (774c666)
Added diamond search ME algorithm (4e13608)
Enabled low delay B GOP structure with --bipred --gop=lp-g4d3t1 (7155dd0)
Added termination of intra search at zero residual with --intra-rdo-et (4fb1c16)
Optimization
Made TZ search faster and slightly better (c136044)
Optimized bi-prediction (69756e2)
Fixes
Fixed transform skip with rectangular inter blocks (fb462b2)
Fixed accidental inter search for 4x4 blocks (649113a)
User Interface
Changed options for all preset levels (f033ad0)
Added an option for limiting the number of steps in motion estimation with --me-steps (39ed368)
Added --me=dia (4e13608)
Added --level, --force-level and --high-tier for setting bitstream level and tier (bac0745)
Building
Fixed issue with struct timespec redefinition with Visual Studio 2015 and later (713e694)
Fixed building .asm files in Visual Studio 2017 (6be8195)
Fixed compatibility with crypto++ 6.0 (4b24cd0)
Added support for crypto++ with the name libcryptopp (411276d)
Dockerfile base image was updated to Ubuntu 18.04 (8380b6c)
Enabled -Wextra by default (ff17e0b)
Refactoring
Inter motion vector cost functions (c73cce3)
Dockerfile (0164291)
BD-Bitrate
Average BD-Bitrate compared with v1.2:
Class0-uf1-sf2-vf3-fr4-f5-m6-s7-sr8-vs
hevc-A-18.8 %-17.5 %-1.7 %-6.2 %-2.1 %-6.1 %-8.7 %-19.1 %-19.2 %
hevc-B-21.3 %-20.9 %-4.6 %-5.7 %-2.9 %-6.6 %-11.8 %-26.4 %-23.9 %
hevc-C-26.6 %-24.9 %-2.4 %-8.3 %-3.7 %-11.9 %-11.0 %-26.1 %-21.0 %
hevc-D-33.3 %-31.1 %-1.8 %-11.5 %-7.5 %-16.5 %-16.2 %-28.9 %-23.6 %
hevc-E-26.3 %-25.3 %-20.4 %-15.4 %-13.8 %-15.7 %-21.3 %-26.3 %-25.9 %
hevc-F-9.2 %-8.4 %-5.2 %-4.9 %-3.0 %-20.8 %-17.3 %0.2 %18.8 %
Total-22.7 %-21.5 %-5.7 %-8.4 %-5.3 %-13.2 %-14.4 %-21.3 %-15.4 %
Speedup
Average speedup compared with v1.2 on an Intel Xeon E5-2620 v4 machine:
class0-uf1-sf2-vf3-fr4-f5-m6-s7-sr8-vs
hevc-Ax0.88x0.91x1.02x1.19x1.37x0.76x0.93x0.58x0.36
hevc-Bx0.90x0.92x1.08x1.21x1.40x0.81x0.99x0.62x0.38
hevc-Cx0.87x0.88x0.96x1.11x1.24x0.59x0.72x0.40x0.26
hevc-Dx0.92x0.97x1.03x1.23x1.34x0.65x0.74x0.38x0.27
hevc-Ex0.97x0.94x1.08x1.15x1.34x0.86x1.05x0.74x0.54
hevc-Fx0.81x0.91x1.01x1.09x1.30x0.78x0.88x0.49x0.35
Totalx0.89x0.92x1.03x1.17x1.33x0.74x0.88x0.53x0.35
Assets
7
v1.2.0
Nov 17, 2017
@ari-koivula ari-koivula
v1.2.0
cf85d52
v1.2.0
We are happy to release Kvazaar version 1.2. Since the last version, Kvazaar has obtained significant speedups at all presets and the compression efficiency has improved for the fastest presets. Please find the complete list of changes below.
Features
Intra prediction mode encryption with --crypto=intra_pred_modes (2b8ce5e)
Adaptive QP for 360° video with --erp-aqp (26adef4)
New selection algorithm for --owf=auto and --threads=auto (8c4a347)
Added an option to set the encryption key using --key (2e13091)
Added an option to limit SAO to band offset or edge offset only with --sao=band and --sao=edge (8674c0f)
Optimization
Reduced number of intra modes checked when using --rd=2 (2cad317)
Reduced inter-frame CTU dependencies caused by SAO (050e90d)
Changed to a faster calculation for coefficient costs when using --rd=0 (1ead9c0)
Fixes
Fixed long motion vectors not getting clipped (#158, 85e2a40)
Fixed order of pictures in reconstruction debug output when --gop=8 is used (#101, aae141f)
Fixed a use-after-free when encoding very few frames with --gop=8 (#161, 2991962)
Fixed a crash when video size is not a multiple of the smallest CU size (2f2405d)
Fixed invalid bitstream when QP is too large (382636d)
Fixed a race condition causing a deadlock (5f8e17d)
Fixed a memory leak in encryption (8654b48)
Fixed I-frames not being IRAP frames when using GOP (00c9f52, 841597e)
Fixed computing inter and intra costs with different metrics (afc13f1)
Fixed reliance on undefined behavior (b41f0fa, 924cf85)
Fixed --mv-constraint=frametilemargin constraining motion vectors too much (409d211)
Fixed using --bipred with --tmvp (#160, 9974380)
User Interface
Changed type of kvz_config.roi.dqps from uint8_t* to int8_t. Delta QP values for --roi may now be negative. (79cb3a2)
Changed PSNR display format (20d6444)
Building
Default to no -Werror. Run configure with --enable-werror to enable it. (033bc6b)
make check now runs valgrind tests that used to only run on Travis. Programs ffmpeg, valgrind and TAppDecoderStatic should be found from $PATH (6bbe5e1)
Refactoring
Removed duplicate code in inter MVP and merge candidate selection (4fb0783)
Removed duplicate code in intra reconstruction for luma and chroma (e944416)
Changed functions for writing the CU tree bitstream to use luma pixel coordinates (610c91b, f5eef7f)
Removed duplicate code in functions for writing intra CU bitstream with and without encryption (525a518)
Removed duplicate code in helper functions in search.c (2c73476)
Gathered function parameters for inter search functions into a single struct (2fa3d82)
BD-Bitrate
Average BD-Bitrate compared with v1.1:
Class0-uf1-sf2-vf3-fr4-f5-m6-s7-sr8-vs
hevc-A-15.71 %-6.68 %-4.66 %-0.89 %-1.11 %-0.54 %+0.04 %-0.02 %+0.32 %
hevc-B-19.04 %-8.15 %-6.92 %-1.26 %-1.48 %-0.65 %-0.33 %-0.33 %-0.07 %
hevc-C-20.39 %-8.54 %-5.01 %-0.55 %-0.72 %-0.44 %+0.03 %-0.00 %+0.23 %
hevc-D-13.24 %-5.15 %-2.54 %-0.33 %-0.51 %-0.32 %-0.10 %-0.04 %+0.13 %
hevc-E-4.37 %-3.31 %-1.90 %-0.52 %-1.10 %-0.68 %-0.74 %-0.86 %-0.78 %
hevc-F-12.42 %-6.15 %-5.25 %+0.04 %+0.24 %+0.25 %+0.32 %+0.70 %+0.90 %
Total-14.80 %-6.59 %-4.68 %-0.60 %-0.78 %-0.39 %-0.13 %-0.08 %+0.14 %
Speedup
Average speedup compared with v1.1 on an Intel Core i7-4770 machine:
Class0-uf1-sf2-vf3-fr4-f5-m6-s7-sr8-vs
hevc-Ax1.07x1.06x1.10x1.10x1.09x1.11x1.10x1.11x1.10
hevc-Bx1.06x1.07x1.09x1.11x1.09x1.13x1.12x1.13x1.14
hevc-Cx1.22x1.27x1.32x1.35x1.33x1.37x1.39x1.42x1.41
hevc-Dx1.34x1.58x1.64x1.60x1.58x1.54x1.55x1.57x1.54
hevc-Ex1.20x1.17x1.16x1.18x1.16x1.17x1.16x1.20x1.19
hevc-Fx1.25x1.20x1.20x1.23x1.20x1.24x1.24x1.27x1.27
Totalx1.19x1.22x1.24x1.26x1.24x1.26x1.26x1.28x1.28
Assets
5
v1.1.0
Feb 16, 2017
@ari-koivula ari-koivula
v1.1.0
7369f25
v1.1.0
I think there are enough new features to call this v1.1.0.
Average BD bitrate (QP 17, 22, 27, 32) v1.1.0 vs v1.0.0
Class0-uf1-sf2-vf3-fr4-f5-m6-s7-sr8-vs
A-1.9%-1.5%-1.2%-1.0%-0.7%-0.7%-1.1%-1.1%-1.3%
B-2.2%-1.3%-1.4%-0.8%-0.5%-0.6%-0.9%-0.8%-1.0%
C-1.3%-1.1%-1.0%-0.9%-0.6%-0.6%-0.6%-0.6%-0.8%
D-1.1%-0.9%-0.7%-0.7%-0.6%-0.5%-0.1%-0.2%-0.4%
E-2.5%-1.5%-0.9%-0.7%-0.3%-0.3%-0.5%-0.4%-0.4%
F-1.6%-0.7%-0.9%-0.8%-0.5%-0.4%-0.7%-0.7%-0.7%
All-1.7%-1.2%-1.0%-0.8%-0.5%-0.5%-0.6%-0.6%-0.8%
Average speedup (QP 17, 22, 27, 32) v1.1.0 vs v1.0.0
Class0-uf1-sf2-vf3-fr4-f5-m6-s7-sr8-vs
A1.03x1.02x1.01x1.01x1.01x1.02x1.07x1.09x1.16x
B1.03x1.01x1.02x1.01x1.01x1.01x1.06x1.06x1.13x
C1.03x1.02x1.01x1.01x1.01x1.01x1.07x1.07x1.16x
D1.07x1.05x1.03x1.03x1.02x1.02x1.07x1.09x1.17x
E0.99x0.97x0.98x0.99x0.99x0.99x1.00x1.02x1.05x
F1.02x1.01x1.01x1.01x1.01x1.01x1.08x1.09x1.17x
All1.03x1.02x1.01x1.01x1.01x1.01x1.06x1.07x1.14x
Paramaters: --threads=4 --owf=1 -p64
Features
Bitrate control now works at LCU level, giving more consistent results. (2318bd7)
Added --roi parameter for LCU level delta-QP control. (4a0121a)
Added --slices parameter for encapsulating tiles and WPP-rows into slice NAL's instead of using bitstream offsets. (1e6463c)
Temporal motion vector prediction now works with B-frames. (d892be5)
Optimization
Added AVX2 version of SSD. (778e46d)
Optimized intra reference building. (c31207e)
Optimized bitstream writes. (a9e45ef)
Optimized CU-split decision. (2c069a3)
Fix main-thread busy-looping on Linux. (a5a925f)
Avoid initializing memory needlessly during RDOQ. (acd12cb, b021d22)
Fixes
Pass DTS and PTS timestamps correctly through the API. (d18de19)
Fixed bug with subpixel motion estimation within tiles. (2c005cd)
Improved 10-bit RD-performance. (70a52f0)
Fixed for stupendously large bitstreams when --mv-constraint was used with --subme. (937a764)
Fixed bug with --smp and --amp. (46c9a48)
Fix problem with --bipred. (1e6463c)
Fixed hang with threading on OSX. (d893474)
Fix crash when frame is less than 65 pixels high and WPP is used. (b8e3513)
User Interface
Disabled WPP with tiles enabled. (cb6672b)
Improved --help. (5bf7454, 78a28e0)
Made it possible to disable the gop-structure that was enabled by default in v.1.0.0. (deb63f7)
Have --threads=auto enable threading instead of disabling it. (db5e750)
Give errors on failures and handle them better. (97863cd, 6a178de)
Use reference picture number of medium preset by default. (7ff33e1)
Building
Include optimizations on 32-bit. (1dcc993)
Added appveyor CI tests for MSYS2. (e269b86)
Add pkg-config macros, so pkg-config doesn't need to be installed anymore. (2d7daa1)
Travis CI OSX tests work again. (c32f5fa)
Refactoring
Refactored deblocking and sign hiding. (7ec5f78)
Removed Exp-Golomb lookup table. (ed3bd89)
Copy kvz_config to encoder_control_t and remove duplicate fields. (e78a8df)
Assets
5
v1.0.0
Oct 4, 2016
@ari-koivula ari-koivula
v1.0.0
e7cdd47
v1.0.0
It's been 9 months since last release. Now that the encoder just got 10x faster (on veryslow), and quite a bit faster and better on every other preset as well, I think it's time for a major verson bump.
Average BD bitrate (QP 17, 22, 27, 32) v1.0.0 vs v0.8.3
Class0-uf1-sf2-vf3-fr4-f5-m6-s7-sr8-vs
A-16.4%-26.9%-27.5%-31.0%-11.2%-11.9%-11.3%-6.7%-4.8%
B-16.2%-33.7%-31.7%-37.6%-11.6%-14.8%-15.7%-9.1%-6.3%
C-7.0%-17.6%-28.0%-31.2%-8.3%-9.0%-11.3%-7.1%-8.1%
D-3.7%-12.3%-29.2%-30.3%-5.4%-5.9%-11.5%-8.3%-9.9%
E-28.4%-42.6%-33.5%-39.4%-22.6%-28.5%-20.3%-7.0%-0.7%
F-6.1%-11.3%-12.8%-16.5%-10.1%-2.1%2.3%10.8%6.4%
|
|All|-13.0%|-24.1%|-27.1%|-31.0%|-11.5%|-12.0%|-11.3%| -4.6%| -3.9%|
Average speedup (QP 17, 22, 27, 32) v1.0.0 vs v0.8.3
Class0-uf1-sf2-vf3-fr4-f5-m6-s7-sr8-vs
A1.61x1.91x1.89x1.37x2.69x3.33x4.79x7.32x11.06x
B1.65x1.98x1.96x1.46x2.67x3.36x4.79x8.15x13.89x
C1.76x1.97x1.98x1.45x2.52x2.97x4.87x9.32x15.77x
D2.09x1.87x1.81x1.32x1.97x2.36x5.13x8.78x12.65x
E1.91x1.96x1.75x1.40x3.00x3.70x4.87x6.06x7.56x
F1.84x1.83x1.74x1.41x2.86x2.98x4.60x8.18x13.58x
|
|All|1.81x|1.92x|1.86x|1.40x|2.62x|3.12x|4.84x|7.97x|12.42x|
Paramaeters: --threads=4 --owf=1 --wpp -p64
New Features
--version
--help
--loop-input
--mv-constraint to constrain motion vectors
--tiles=2x2 as an alternative syntax for uniform tiles
--hash=md5
Print information about what SIMD optimizations are in use
--mv=full8 --mv=full16 --mv=full32 --mv=full64
--cu-split-termination=zero/off
--crypto for selective encryption of bitstream (for OpenHEVC)
--me-early-termination=sensitive/on/off for early termination of motion vector search
Added 4x8 SMP and 4x12 AMP motion partitions
--subme=0/1/2/3/4 for control over complexity of fractional pixel motion prediction
--lossless for lossless coding
Monochrome coding
--input-format=420/400
--input-bitdepth=8/10
--tmpv for temporal motion vector predictor
--rdoq-skip for not using rdoq for situations where it's unlikely to improve BDRate
Modified --gop=lp-g4d3r1t1 syntax to not take the reference frames as a parameter, it's now --gop=lp-g4d3t1.
Enable WPP and multithreading by default, with detection for number of cores
Update all presets to ratedistortion-complexity optimized versions. These are based on a search of all (~ish) possible encoding parameters and bring a huge boost to both speed and BDRate when encoding with the presets (10x speed for veryslow, ~1.1x-4x for others, up to 30% improved BDRate for some presets).
Set default options to match medium with intra period of 64, QP 22 and --gop=lp-g4d3t1
--implicit-rdpcm RExt feature
Optimizations
AVX2 version for Sample Adaptive Offset (SAO)
Optimized memory copying
AVX2 versions of filters for fractional pixel motion estimation
AVX2 version for half pixel chroma sampling for SMP/AMP
AVX2 versions for calculating two or four SATD values at once for small blocks
Rewrote AVX2 version of fractional pixel motion compensation
Rewrote motion vector cost calculation. It only got slightly faster, but BDRate improved a bunch due to the new implementation being more correct.
Made AVX2 SAD use SSE4.1 for cases where there isn't an AVX2 implementation, speeding up SMP/AMP.
Bugfixes
Fixed a bug in rate control where an int overflowed after coding 2^31 bits (2Gb)
Fixed non-determinism intiles
Fixed chroma reconstruction bug in tiles
Fixed a bug with calculating the number of bits used for intra mode on 4x4 CUs
Stopped checking zero motion vector multiple times in motion compensation
Fixed possible segfault in motion compensation
Fixed a race condition with OWF and SMP/AMP
Gave pthread_cond_timedwait time in correctly, such that main thread now sleeps instead of busylooping when it has nothing to do
Fixed rate control with lp-gop
Fixed full search not taking temporal motion vector into account
Allow non-gop-length intra period for lp-gop
Code / Building / Testing
Moved SAO to it's own file
Removed a ton of unnecessary includes
Updated autotools ax_pthread
Added build test for OS-X for Travis
Made tests check for bitstream correctness
Refactored some of the copypasta in motion vector search starting point selection
Refactored the cu_info_t datastructures to hold information at a 4x4 resolution needed for AMP and SMP
Changed cu_info_t to use bitfields to negate the effect of increasing the cu_info_t array by a factor of 4
Moved bitstream generation from encoderstate.c to encode_coding_tree.c
Renamed encoder_state_t.global to frame, which makes sense since it hold frame level data, not global data
Rewrote integer vector inter prediction, because it was so bad
Refactored init_lcu_t
Added more tests for inter SAD
Added speed tests for dual intra SAD functions
Added more realistic speed tests for inter SAD
Other
Added a manpage
Added scripts for updating manpage and README based on --usage.
Added a Dockerfile. Just because.
Added commit date to --version