[x265] [PATCH] Add real-time VBV fullness based QP tuning in VBV 2 pass
Kirithika Kalirathnam
kirithika at multicorewareinc.com
Fri Sep 4 14:13:52 CEST 2020
>From f1391f094c9c3c0502624532f751219d126905aa Mon Sep 17 00:00:00 2001
From: Kirithika <kirithika at multicorewareinc.com>
Date: Fri, 28 Aug 2020 09:20:47 +0530
Subject: [PATCH] Add real-time VBV fullness based QP tuning in VBV 2 pass
This commit enables real-time VBV fullness based 2nd pass QP tuning.
Experimental feature.Default disabled
---
doc/reST/cli.rst | 9 +++
source/CMakeLists.txt | 2 +-
source/common/param.cpp | 12 ++++
source/encoder/ratecontrol.cpp | 100 ++++++++++++++++++---------------
source/encoder/slicetype.cpp | 14 +++--
source/x265.h | 4 ++
source/x265cli.cpp | 1 +
source/x265cli.h | 2 +
8 files changed, 92 insertions(+), 52 deletions(-)
diff --git a/doc/reST/cli.rst b/doc/reST/cli.rst
index e6c628c36..2a4b25aca 100755
--- a/doc/reST/cli.rst
+++ b/doc/reST/cli.rst
@@ -1977,6 +1977,15 @@ Quality, rate control and rate distortion options
**Range of values:** 0 to 10
+.. option:: --realtime-vbv-2pass, --no-realtime-vbv-2pass
+
+ It enables the Qp tuning at frame level based on real time VBV Buffer
fullness
+ in the ratecontrol second pass to reduce the VBV violations.
+ It could only be enabled with rate control pass 2 encodes with VBV and
ABR
+ rate control mode.
+
+ Default disabled. **Experimental feature**
+
Quantization Options
====================
diff --git a/source/CMakeLists.txt b/source/CMakeLists.txt
index d9ed3983e..5738c861c 100755
--- a/source/CMakeLists.txt
+++ b/source/CMakeLists.txt
@@ -29,7 +29,7 @@ option(NATIVE_BUILD "Target the build CPU" OFF)
option(STATIC_LINK_CRT "Statically link C runtime for release builds" OFF)
mark_as_advanced(FPROFILE_USE FPROFILE_GENERATE NATIVE_BUILD)
# X265_BUILD must be incremented each time the public API is changed
-set(X265_BUILD 196)
+set(X265_BUILD 197)
configure_file("${PROJECT_SOURCE_DIR}/x265.def.in"
"${PROJECT_BINARY_DIR}/x265.def")
configure_file("${PROJECT_SOURCE_DIR}/x265_config.h.in"
diff --git a/source/common/param.cpp b/source/common/param.cpp
index 845c38bd2..fc0425905 100755
--- a/source/common/param.cpp
+++ b/source/common/param.cpp
@@ -288,6 +288,7 @@ void x265_param_default(x265_param* param)
param->bResetZoneConfig = 1;
param->reconfigWindowSize = 0;
param->decoderVbvMaxRate = 0;
+ param->rc.bRealtimeVBV2pass = 0;
/* Video Usability Information (VUI) */
param->vui.aspectRatioIdc = 0;
@@ -1375,6 +1376,7 @@ int x265_param_parse(x265_param* p, const char* name,
const char* value)
sscanf(value, "%d,%d,%d", &p->hmeRange[0], &p->hmeRange[1],
&p->hmeRange[2]);
p->bEnableHME = true;
}
+ OPT("realtime-vbv-2pass") p->rc.bRealtimeVBV2pass = atobool(value);
else
return X265_PARAM_BAD_NAME;
}
@@ -1817,6 +1819,15 @@ int x265_check_params(x265_param* param)
CHECK(param->confWinRightOffset < 0, "Conformance Window Right Offset
must be 0 or greater");
CHECK(param->confWinBottomOffset < 0, "Conformance Window Bottom
Offset must be 0 or greater");
CHECK(param->decoderVbvMaxRate < 0, "Invalid Decoder Vbv Maxrate.
Value can not be less than zero");
+ if (param->rc.bRealtimeVBV2pass)
+ {
+ CHECK((param->rc.bStatRead == 0), "Real time VBV in 2 pass option
requires rate control 2 pass to be enabled");
+ if ((param->rc.vbvMaxBitrate <= 0 || param->rc.vbvBufferSize <= 0))
+ {
+ param->rc.bRealtimeVBV2pass = 0;
+ x265_log(param, X265_LOG_WARNING, "Real time VBV enabled
without VBV settings.Disabling real time VBV in 2 pass\n");
+ }
+ }
return check_failed;
}
@@ -2593,6 +2604,7 @@ void x265_copy_params(x265_param* dst, x265_param*
src)
dst->confWinRightOffset = src->confWinRightOffset;
dst->confWinBottomOffset = src->confWinBottomOffset;
+ dst->rc.bRealtimeVBV2pass = src->rc.bRealtimeVBV2pass;
#ifdef SVT_HEVC
memcpy(dst->svtHevcParam, src->svtHevcParam,
sizeof(EB_H265_ENC_CONFIGURATION));
#endif
diff --git a/source/encoder/ratecontrol.cpp b/source/encoder/ratecontrol.cpp
index 82d7c4f2a..ebf374759 100644
--- a/source/encoder/ratecontrol.cpp
+++ b/source/encoder/ratecontrol.cpp
@@ -1755,34 +1755,32 @@ double RateControl::rateEstimateQscale(Frame*
curFrame, RateControlEntry *rce)
g_sliceTypeToChar[m_sliceType],
g_sliceTypeToChar[rce->sliceType]);
}
}
- else
+
+ if ((m_param->rc.bRealtimeVBV2pass && m_param->rc.rateControlMode ==
X265_RC_ABR) || m_isAbr)
{
- if (m_isAbr)
+ int pos = m_sliderPos % s_slidingWindowFrames;
+ int addPos = (pos + s_slidingWindowFrames - 1) %
s_slidingWindowFrames;
+ if (m_sliderPos > s_slidingWindowFrames)
{
- int pos = m_sliderPos % s_slidingWindowFrames;
- int addPos = (pos + s_slidingWindowFrames - 1) %
s_slidingWindowFrames;
- if (m_sliderPos > s_slidingWindowFrames)
- {
- const static double base = pow(0.5, s_slidingWindowFrames
- 1);
- m_movingAvgSum -= m_lastRemovedSatdCost * base;
- m_movingAvgSum *= 0.5;
- m_movingAvgSum += m_satdCostWindow[addPos];
- }
- else if (m_sliderPos == s_slidingWindowFrames)
- {
- m_movingAvgSum += m_satdCostWindow[addPos];
- }
- else if (m_sliderPos > 0)
- {
- m_movingAvgSum += m_satdCostWindow[addPos];
- m_movingAvgSum *= 0.5;
- }
-
- rce->movingAvgSum = m_movingAvgSum;
- m_lastRemovedSatdCost = m_satdCostWindow[pos];
- m_satdCostWindow[pos] = rce->lastSatd;
- m_sliderPos++;
+ const static double base = pow(0.5, s_slidingWindowFrames - 1);
+ m_movingAvgSum -= m_lastRemovedSatdCost * base;
+ m_movingAvgSum *= 0.5;
+ m_movingAvgSum += m_satdCostWindow[addPos];
+ }
+ else if (m_sliderPos == s_slidingWindowFrames)
+ {
+ m_movingAvgSum += m_satdCostWindow[addPos];
}
+ else if (m_sliderPos > 0)
+ {
+ m_movingAvgSum += m_satdCostWindow[addPos];
+ m_movingAvgSum *= 0.5;
+ }
+
+ rce->movingAvgSum = m_movingAvgSum;
+ m_lastRemovedSatdCost = m_satdCostWindow[pos];
+ m_satdCostWindow[pos] = rce->lastSatd;
+ m_sliderPos++;
}
if (m_sliceType == B_SLICE)
@@ -1887,7 +1885,7 @@ double RateControl::rateEstimateQscale(Frame*
curFrame, RateControlEntry *rce)
qScale = x265_clip3(lqmin, lqmax, qScale);
}
- if (!m_2pass)
+ if (!m_2pass || m_param->rc.bRealtimeVBV2pass)
{
/* clip qp to permissible range after vbv-lookahead
estimation to avoid possible
* mispredictions by initial frame size predictors */
@@ -1955,7 +1953,9 @@ double RateControl::rateEstimateQscale(Frame*
curFrame, RateControlEntry *rce)
else
q /= zone->bitrateFactor;
}
- q /= x265_clip3(0.5, 2.0, (double)(abrBuffer - diff) /
abrBuffer);
+ /*Existing ABR conformance check may not be valid with real
time VBV*/
+ if(!m_param->rc.bRealtimeVBV2pass)
+ q /= x265_clip3(0.5, 2.0, (double)(abrBuffer - diff) /
abrBuffer);
if (m_expectedBitsSum > 0)
{
/* Adjust quant based on the difference between
@@ -1988,24 +1988,34 @@ double RateControl::rateEstimateQscale(Frame*
curFrame, RateControlEntry *rce)
if (m_isVbv)
{
- /* Do not overflow vbv */
- double expectedSize = qScale2bits(rce, q);
- double expectedVbv = m_bufferFill + m_bufferRate -
expectedSize;
- double expectedFullness = rce->expectedVbv / m_bufferSize;
- double qmax = q * (2 - expectedFullness);
- double sizeConstraint = 1 + expectedFullness;
- qmax = X265_MAX(qmax, rce->newQScale);
- if (expectedFullness < .05)
- qmax = lmax;
- qmax = X265_MIN(qmax, lmax);
- while (((expectedVbv < rce->expectedVbv/sizeConstraint) &&
(q < qmax)) ||
+ if (!m_param->rc.bRealtimeVBV2pass)
+ {
+ /* Do not overflow vbv */
+ double expectedSize = qScale2bits(rce, q);
+ double expectedVbv = m_bufferFill + m_bufferRate -
expectedSize;
+ double expectedFullness = rce->expectedVbv /
m_bufferSize;
+ double qmax = q * (2 - expectedFullness);
+ double sizeConstraint = 1 + expectedFullness;
+ qmax = X265_MAX(qmax, rce->newQScale);
+ if (expectedFullness < .05)
+ qmax = lmax;
+ qmax = X265_MIN(qmax, lmax);
+ while (((expectedVbv < rce->expectedVbv /
sizeConstraint) && (q < qmax)) ||
((expectedVbv < 0) && (q < lmax)))
+ {
+ q *= 1.05;
+ expectedSize = qScale2bits(rce, q);
+ expectedVbv = m_bufferFill + m_bufferRate -
expectedSize;
+ }
+ }
+ else
{
- q *= 1.05;
- expectedSize = qScale2bits(rce, q);
- expectedVbv = m_bufferFill + m_bufferRate -
expectedSize;
+ /* clip qp to permissible range after
vbv-lookahead estimation to avoid possible
+ * mispredictions by Rate Control pass 1 statistics
analysis */
+ q = clipQscale(curFrame, rce, q);
}
}
+
q = x265_clip3(lmin, lmax, q);
}
else
@@ -2301,7 +2311,7 @@ double RateControl::clipQscale(Frame* curFrame,
RateControlEntry* rce, double q)
double lmin = m_lmin[rce->sliceType];
double lmax = m_lmax[rce->sliceType];
double q0 = q;
- if (m_isVbv && m_currentSatd > 0 && curFrame)
+ if ((m_isVbv || m_param->rc.bRealtimeVBV2pass) && curFrame &&
m_currentSatd > 0 )
{
if (m_param->lookaheadDepth || m_param->rc.cuTree ||
(m_param->scenecutThreshold || m_param->bHistBasedSceneCut) ||
@@ -2379,7 +2389,7 @@ double RateControl::clipQscale(Frame* curFrame,
RateControlEntry* rce, double q)
}
/* Try to get the buffer not more than 80% filled, but
don't set an impossible goal. */
targetFill = x265_clip3(m_bufferSize * (1 - 0.2 *
finalDur), m_bufferSize, m_bufferFill - totalDuration * m_vbvMaxRate * 0.5);
- if (m_isCbr && bufferFillCur > targetFill &&
!m_isSceneTransition)
+ if ((m_isCbr || m_2pass) && bufferFillCur > targetFill
&& !m_isSceneTransition)
{
q /= 1.01;
loopTerminate |= 2;
@@ -2432,7 +2442,7 @@ double RateControl::clipQscale(Frame* curFrame,
RateControlEntry* rce, double q)
* lookahead vbv reduces its qscale by half its value. Be on safer
side and avoid drastic
* qscale reductions for frames high in complexity */
bool mispredCheck = rce->movingAvgSum && m_currentSatd >=
rce->movingAvgSum && q <= q0 / 2;
- if (!m_isCbr || (m_isAbr && mispredCheck))
+ if (!m_isCbr || ((m_isAbr || m_2pass) && mispredCheck))
q = X265_MAX(q0, q);
if (m_rateFactorMaxIncrement)
@@ -2442,7 +2452,7 @@ double RateControl::clipQscale(Frame* curFrame,
RateControlEntry* rce, double q)
return x265_clip3(lmin, qmax, q);
}
}
- if (m_2pass)
+ if (!curFrame && m_2pass)
{
double min = log(lmin);
double max = log(lmax);
diff --git a/source/encoder/slicetype.cpp b/source/encoder/slicetype.cpp
index 4e52e584c..69f3b0ad1 100644
--- a/source/encoder/slicetype.cpp
+++ b/source/encoder/slicetype.cpp
@@ -1497,14 +1497,15 @@ void Lookahead::slicetypeDecide()
}
}
- if (m_lastNonB && !m_param->rc.bStatRead &&
+ if (m_lastNonB &&
((m_param->bFrameAdaptive && m_param->bframes) ||
m_param->rc.cuTree || m_param->scenecutThreshold ||
m_param->bHistBasedSceneCut ||
(m_param->lookaheadDepth && m_param->rc.vbvBufferSize)))
{
- slicetypeAnalyse(frames, false);
+ if(!m_param->rc.bStatRead)
+ slicetypeAnalyse(frames, false);
bool bIsVbv = m_param->rc.vbvBufferSize > 0 &&
m_param->rc.vbvMaxBitrate > 0;
- if (m_param->analysisLoad && m_param->scaleFactor && bIsVbv)
+ if ((m_param->analysisLoad && m_param->scaleFactor && bIsVbv) ||
m_param->rc.bRealtimeVBV2pass)
{
int numFrames;
for (numFrames = 0; numFrames < maxSearch; numFrames++)
@@ -1749,7 +1750,7 @@ void Lookahead::slicetypeDecide()
}
}
- bool isKeyFrameAnalyse = (m_param->rc.cuTree ||
(m_param->rc.vbvBufferSize && m_param->lookaheadDepth)) &&
!m_param->rc.bStatRead;
+ bool isKeyFrameAnalyse = (m_param->rc.cuTree ||
(m_param->rc.vbvBufferSize && m_param->lookaheadDepth));
if (isKeyFrameAnalyse && IS_X265_TYPE_I(m_lastNonB->sliceType))
{
m_inputLock.acquire();
@@ -1764,9 +1765,10 @@ void Lookahead::slicetypeDecide()
m_inputLock.release();
frames[j + 1] = NULL;
- slicetypeAnalyse(frames, true);
+ if (!m_param->rc.bStatRead)
+ slicetypeAnalyse(frames, true);
bool bIsVbv = m_param->rc.vbvBufferSize > 0 &&
m_param->rc.vbvMaxBitrate > 0;
- if (m_param->analysisLoad && m_param->scaleFactor && bIsVbv)
+ if ((m_param->analysisLoad && m_param->scaleFactor && bIsVbv) ||
m_param->rc.bRealtimeVBV2pass)
{
int numFrames;
for (numFrames = 0; numFrames < maxSearch; numFrames++)
diff --git a/source/x265.h b/source/x265.h
index 0ffa600b0..bcd1d4e58 100644
--- a/source/x265.h
+++ b/source/x265.h
@@ -1486,6 +1486,10 @@ typedef struct x265_param
/* internally enable if tune grain is set */
int bEnableConstVbv;
+ /*Enables Qp tuning with respect to real time VBV buffer fullness
in rate
+ control 2 pass. Experimental.Default is disabled*/
+ int bRealtimeVBV2pass;
+
} rc;
/*== Video Usability Information ==*/
diff --git a/source/x265cli.cpp b/source/x265cli.cpp
index 6e8e0e661..0b17a8d3a 100755
--- a/source/x265cli.cpp
+++ b/source/x265cli.cpp
@@ -221,6 +221,7 @@ namespace X265_NS {
" - 3 : Nth pass, overwrites
stats file\n");
H0(" --[no-]multi-pass-opt-analysis Refine analysis in 2 pass
based on analysis information from pass 1\n");
H0(" --[no-]multi-pass-opt-distortion Use distortion of CTU from
pass 1 to refine qp in 2 pass\n");
+ H0(" --[no-]realtime-vbv-2pass Enable realtime VBV in rate
control 2 pass.Default %s\n", OPT(param->bLossless));
H0(" --stats Filename for stats file in
multipass pass rate control. Default x265_2pass.log\n");
H0(" --[no-]analyze-src-pics Motion estimation uses source
frame planes. Default disable\n");
H0(" --[no-]slow-firstpass Enable a slow first pass in a
multipass rate control mode. Default %s\n",
OPT(param->rc.bEnableSlowFirstPass));
diff --git a/source/x265cli.h b/source/x265cli.h
index 311f06935..89840d9af 100644
--- a/source/x265cli.h
+++ b/source/x265cli.h
@@ -284,6 +284,8 @@ static const struct option long_options[] =
{ "no-multi-pass-opt-analysis", no_argument, NULL, 0 },
{ "multi-pass-opt-distortion", no_argument, NULL, 0 },
{ "no-multi-pass-opt-distortion", no_argument, NULL, 0 },
+ { "realtime-vbv-2pass", no_argument, NULL, 0 },
+ { "no-realtime-vbv-2pass", no_argument, NULL, 0 },
{ "slow-firstpass", no_argument, NULL, 0 },
{ "no-slow-firstpass", no_argument, NULL, 0 },
{ "multi-pass-opt-rps", no_argument, NULL, 0 },
--
2.28.0.windows.1
*Thanks,*
*Kirithika*
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mailman.videolan.org/pipermail/x265-devel/attachments/20200904/82e4c8ea/attachment-0001.html>
-------------- next part --------------
A non-text attachment was scrubbed...
Name: patch-vbv-exp.patch
Type: application/octet-stream
Size: 16360 bytes
Desc: not available
URL: <http://mailman.videolan.org/pipermail/x265-devel/attachments/20200904/82e4c8ea/attachment-0001.obj>
More information about the x265-devel
mailing list