最近刚接触量化部分的代码,简单记录一下。
在VVC中,量化可以分为三种,普通量化,率失真优化量化(RDOQ),依赖量化(DQ),这里主要介绍RDOQ。
率失真优化量化RDOQ
它的主要思想是将量化过程同率失真优化(RDO)准则相结合,选出最优的量化值。
主要实现方法和步骤如下:
- 确定当前TU每个系数的可选量化值,用当前TU所有系数进行预量化,过程类似于普通量化。
- 每一个预量化之后的数值可以得到多个可选值,遍历所有可选值,找到rdcost最小的值最为最优值。遍历整个TU。
- 利用RDO准则确定当前TU每一个系数块组(CG,4x4的块)是否量化成全零组。如果当前的CG是全零CG,那么只需要编码全零标志;否则,要编码所有的系数。具体是:遍历所有的CG,计算其量化为全零CG时的率失真代价,与原来的率失真代价比较,如果全零CG对应的率失真代价较小,那么令当前CG为全零CG。
- 利用ROD准则选择出最优的“最后一个非零系数”的位置,将之后位置的系数置零。
代码实现过程大概600行,对自己看懂的地方做了注释以及一些自带的英文注释。欢迎指正,交流。
void QuantRDOQ::xRateDistOptQuant(TransformUnit &tu, const ComponentID &compID, const CCoeffBuf &pSrc, TCoeff &uiAbsSum, const QpParam &cQP, const Ctx &ctx)
{
const FracBitsAccess& fracBits = ctx.getFracBitsAcess();
const SPS &sps = *tu.cs->sps;
const CompArea &rect = tu.blocks[compID];
const uint32_t uiWidth = rect.width;
const uint32_t uiHeight = rect.height;
const ChannelType chType = toChannelType(compID);
const int channelBitDepth = sps.getBitDepth( chType );
const bool extendedPrecision = sps.getSpsRangeExtension().getExtendedPrecisionProcessingFlag();//扩展精度
const int maxLog2TrDynamicRange = sps.getMaxLog2TrDynamicRange(chType);//最大动态范围
const bool useIntraSubPartitions = tu.cu->ispMode && isLuma(compID);//是否使用ISP
/* for 422 chroma blocks, the effective scaling applied during transformation is not a power of 2, hence it cannot be
* implemented as a bit-shift (the quantised result will be sqrt(2) * larger than required). Alternatively, adjust the
* uiLog2TrSize applied in iTransformShift, such that the result is 1/sqrt(2) the required result (i.e. smaller)
* Then a QP+3 (sqrt(2)) or QP-3 (1/sqrt(2)) method could be used to get the required result
*/
// Represents scaling through forward transform
int iTransformShift = getTransformShift(channelBitDepth, rect.size(), maxLog2TrDynamicRange);//T_shift
#if JVET_P0058_CHROMA_TS
if (tu.mtsIdx[compID] == MTS_SKIP && extendedPrecision)
#else
if (tu.mtsIdx==MTS_SKIP && extendedPrecision)
#endif
{
iTransformShift = std::max<int>(0, iTransformShift);
}
double d64BlockUncodedCost = 0;
const uint32_t uiLog2BlockWidth = floorLog2(uiWidth);
const uint32_t uiLog2BlockHeight = floorLog2(uiHeight);
const uint32_t uiMaxNumCoeff = rect.area();
CHECK(compID >= MAX_NUM_TBLOCKS, "Invalid component ID");
int scalingListType = getScalingListType(tu.cu->predMode, compID);//;根据预测模式选择缩放类型
CHECK(scalingListType >= SCALING_LIST_NUM, "Invalid scaling list");
const TCoeff *plSrcCoeff = pSrc.buf;//变换系数
TCoeff *piDstCoeff = tu.getCoeffs(compID).buf;//量化后系数
double *pdCostCoeff = m_pdCostCoeff;
double *pdCostSig = m_pdCostSig;
double *pdCostCoeff0 = m_pdCostCoeff0;
int *rateIncUp = m_rateIncUp;
int *rateIncDown = m_rateIncDown;
int *sigRateDelta = m_sigRateDelta;
TCoeff *deltaU = m_deltaU;
memset(piDstCoeff, 0, sizeof(*piDstCoeff) * uiMaxNumCoeff);
memset( m_pdCostCoeff, 0, sizeof( double ) * uiMaxNumCoeff );
memset( m_pdCostSig, 0, sizeof( double ) * uiMaxNumCoeff );
memset( m_rateIncUp, 0, sizeof( int ) * uiMaxNumCoeff );
memset( m_rateIncDown, 0, sizeof( int ) * uiMaxNumCoeff );
memset( m_sigRateDelta, 0, sizeof( int ) * uiMaxNumCoeff );
memset( m_deltaU, 0, sizeof( TCoeff ) * uiMaxNumCoeff );
const bool needSqrtAdjustment= TU::needsBlockSizeTrafoScale( tu, compID );
#if JVET_P0058_CHROMA_TS
const bool isTransformSkip = (tu.mtsIdx[compID] == MTS_SKIP);
#else
#if JVET_P0059_CHROMA_BDPCM
const bool isTransformSkip = (tu.mtsIdx == MTS_SKIP && isLuma(compID)) || (tu.cu->bdpcmModeChroma && isChroma(compID));
#else
const bool isTransformSkip = tu.mtsIdx==MTS_SKIP && isLuma(compID);
#endif
#endif
const double *const pdErrScale = xGetErrScaleCoeffSL(scalingListType, uiLog2BlockWidth, uiLog2BlockHeight, cQP.rem(isTransformSkip));
const int *const piQCoef = getQuantCoeff(scalingListType, cQP.rem(isTransformSkip), uiLog2BlockWidth, uiLog2BlockHeight);
const bool enableScalingLists = getUseScalingList(uiWidth, uiHeight, isTransformSkip);//是否使用缩放列表
const int defaultQuantisationCoefficient = g_quantScales[ needSqrtAdjustment ?1:0][cQP.rem(isTransformSkip)];//MF,默认量化系数
const double defaultErrorScale = xGetErrScaleCoeffNoScalingList(scalingListType, uiLog2BlockWidth, uiLog2BlockHeight, cQP.rem(isTransformSkip));
//错误缩放系数
const int iQBits = QUANT_SHIFT + cQP.per(isTransformSkip) + iTransformShift + (needSqrtAdjustment?-1:0); // Right shift of non-RDOQ quantizer; level = (coeff*uiQ + offset)>>q_bits
//qbits=14+QP/6+T_shift+(-1)(非ts)
const TCoeff entropyCodingMinimum = -(1 << maxLog2TrDynamicRange);
const TCoeff entropyCodingMaximum = (1 << maxLog2TrDynamicRange) - 1;
CoeffCodingContext cctx(tu, compID, tu.cs->slice->getSignDataHidingEnabledFlag());
const int iCGSizeM1 = (1 << cctx.log2CGSize()) - 1;
int iCGLastScanPos = -1;
double d64BaseCost = 0;
int iLastScanPos = -1;
int ctxBinSampleRatio = (compID == COMPONENT_Y) ? MAX_TU_LEVEL_CTX_CODED_BIN_CONSTRAINT_LUMA : MAX_TU_LEVEL_CTX_CODED_BIN_CONSTRAINT_CHROMA;
int remRegBins = (uiWidth * uiHeight * ctxBinSampleRatio) >> 4;//对量化后的数值的比特数进行限制,可用数目的size*1.75
uint32_t goRiceParam = 0;
double *pdCostCoeffGroupSig = m_pdCostCoeffGroupSig;
memset( pdCostCoeffGroupSig, 0, ( uiMaxNumCoeff >> cctx.log2CGSize() ) * sizeof( double ) );
int iScanPos;
coeffGroupRDStats rdStats;
#if ENABLE_TRACING
DTRACE( g_trace_ctx, D_RDOQ, "%d: %3d, %3d, %dx%d, comp=%d\n", DTRACE_GET_COUNTER( g_trace_ctx, D_RDOQ ), rect.x, rect.y, rect.width, rect.height, compID );
#endif
const uint32_t lfnstIdx = tu.cu->lfnstIdx;
const int iCGNum = lfnstIdx > 0 ? 1 : std::min<int>(JVET_C0024_ZERO_OUT_TH, uiWidth) * std::min<int>(JVET_C0024_ZERO_OUT_TH, uiHeight) >> cctx.log2CGSize();
//计算系数组CG的数目
for (int subSetId = iCGNum - 1; subSetId >= 0; subSetId--)
{
cctx.initSubblock( subSetId );
uint32_t maxNonZeroPosInCG = iCGSizeM1;//CG中的最大位置
if( lfnstIdx > 0 && ( ( uiWidth == 4 && uiHeight == 4 ) || ( uiWidth == 8 && uiHeight == 8 && cctx.cgPosX() == 0 && cctx.cgPosY() == 0 ) ) )
{
maxNonZeroPosInCG = 7;//特定宽高块 使用lfnst后非零系数所在位置强制为7
}
memset( &rdStats, 0, sizeof (coeffGroupRDStats));
for( int iScanPosinCG = iCGSizeM1; iScanPosinCG > maxNonZeroPosInCG; iScanPosinCG-- )//针对使用lfnst的情况
{
iScanPos = cctx.minSubPos() + iScanPosinCG;//zig-zag扫描后的位置
uint32_t blkPos = cctx.blockPos( iScanPos );//真实位置。从上到下,从左到右数
piDstCoeff[ blkPos ] = 0;//lfnst情况下,其他位置系数设为0
}
for( int iScanPosinCG = maxNonZeroPosInCG; iScanPosinCG >= 0; iScanPosinCG-- )
{
iScanPos = cctx.minSubPos() + iScanPosinCG;
//===== quantization =====
uint32_t uiBlkPos = cctx.blockPos(iScanPos);
// set coeff
const int quantisationCoefficient = (enableScalingLists) ? piQCoef [uiBlkPos] : defaultQuantisationCoefficient;
//选择哪种缩放系数 MF
const double errorScale = (enableScalingLists) ? pdErrScale[uiBlkPos] : defaultErrorScale;
//误差系数
const int64_t tmpLevel = int64_t(abs(plSrcCoeff[ uiBlkPos ])) * quantisationCoefficient;
//tmpLevel=变换系数*缩放系数
const Intermediate_Int lLevelDouble = (Intermediate_Int)std::min<int64_t>(tmpLevel, std::numeric_limits<Intermediate_Int>::max() - (Intermediate_Int(1) << (iQBits - 1)));
uint32_t uiMaxAbsLevel = std::min<uint32_t>(uint32_t(entropyCodingMaximum), uint32_t((lLevelDouble + (Intermediate_Int(1) << (iQBits - 1))) >> iQBits));
//(系数*MF + f')>>qbits, 限值处理
const double dErr = double( lLevelDouble );
pdCostCoeff0[ iScanPos ] = dErr * dErr * errorScale;//每一个系数的量化cost
d64BlockUncodedCost += pdCostCoeff0[ iScanPos ];
piDstCoeff[ uiBlkPos ] = uiMaxAbsLevel;
if ( uiMaxAbsLevel > 0 && iLastScanPos < 0 )
{
iLastScanPos = iScanPos;
iCGLastScanPos = cctx.subSetId();
}
if ( iLastScanPos >= 0 )
{
#if ENABLE_TRACING
uint32_t uiCGPosY = cctx.cgPosX();
uint32_t uiCGPosX = cctx.cgPosY();
uint32_t uiPosY = cctx.posY( iScanPos );
uint32_t uiPosX = cctx.posX( iScanPos );
DTRACE( g_trace_ctx, D_RDOQ, "%d [%d][%d][%2d:%2d][%2d:%2d]", DTRACE_GET_COUNTER( g_trace_ctx, D_RDOQ ), iScanPos, uiBlkPos, uiCGPosX, uiCGPosY, uiPosX, uiPosY );
#endif
//===== coefficient level estimation =====
unsigned ctxIdSig = 0;
if( iScanPos != iLastScanPos )
{
ctxIdSig = cctx.sigCtxIdAbs( iScanPos, piDstCoeff, 0 );
}
uint32_t uiLevel;
uint8_t ctxOffset = cctx.ctxOffsetAbs ();
uint32_t uiParCtx = cctx.parityCtxIdAbs ( ctxOffset );//ctxOffset的奇偶性的索引
uint32_t uiGt1Ctx = cctx.greater1CtxIdAbs ( ctxOffset );//是否大于1的索引
uint32_t uiGt2Ctx = cctx.greater2CtxIdAbs ( ctxOffset );//是否大于2的索引
uint32_t goRiceZero = 0;
if( remRegBins < 4 )
{
unsigned sumAbs = cctx.templateAbsSum( iScanPos, piDstCoeff, 0 );
goRiceParam = g_auiGoRiceParsCoeff [ sumAbs ];
#if JVET_P0170_ZERO_POS_SIMPLIFICATION
goRiceZero = g_auiGoRicePosCoeff0(0, goRiceParam);
#else
goRiceZero = g_auiGoRicePosCoeff0[0][ sumAbs ];
#endif
}
const BinFracBits fracBitsPar = fracBits.getFracBitsArray( uiParCtx );
const BinFracBits fracBitsGt1 = fracBits.getFracBitsArray( uiGt1Ctx );
const BinFracBits fracBitsGt2 = fracBits.getFracBitsArray( uiGt2Ctx );
if( iScanPos == iLastScanPos )
{
//最优uiLevel
uiLevel = xGetCodedLevel( pdCostCoeff[ iScanPos ], pdCostCoeff0[ iScanPos ], pdCostSig[ iScanPos ],
lLevelDouble, uiMaxAbsLevel, nullptr, fracBitsPar, fracBitsGt1, fracBitsGt2, remRegBins, goRiceZero, goRiceParam, iQBits, errorScale, 1, extendedPrecision, maxLog2TrDynamicRange );
}
else
{
DTRACE_COND( ( uiMaxAbsLevel != 0 ), g_trace_ctx, D_RDOQ_MORE, " uiCtxSig=%d", ctxIdSig );
const BinFracBits fracBitsSig = fracBits.getFracBitsArray( ctxIdSig );
uiLevel = xGetCodedLevel( pdCostCoeff[ iScanPos ], pdCostCoeff0[ iScanPos ], pdCostSig[ iScanPos ],
lLevelDouble, uiMaxAbsLevel, &fracBitsSig, fracBitsPar, fracBitsGt1, fracBitsGt2, remRegBins, goRiceZero, goRiceParam, iQBits, errorScale, 0, extendedPrecision, maxLog2TrDynamicRange );
sigRateDelta[ uiBlkPos ] = ( remRegBins < 4 ? 0 : fracBitsSig.intBits[1] - fracBitsSig.intBits[0] );
}
DTRACE( g_trace_ctx, D_RDOQ, " Lev=%d \n", uiLevel );
DTRACE_COND( ( uiMaxAbsLevel != 0 ), g_trace_ctx, D_RDOQ, " CostC0=%d\n", (int64_t)( pdCostCoeff0[iScanPos] ) );
DTRACE_COND( ( uiMaxAbsLevel != 0 ), g_trace_ctx, D_RDOQ, " CostC =%d\n", (int64_t)( pdCostCoeff[iScanPos] ) );
deltaU[ uiBlkPos ] = TCoeff((lLevelDouble - (Intermediate_Int(uiLevel) << iQBits)) >> (iQBits-8));
if( uiLevel > 0 )
{
int rateNow = xGetICRate( uiLevel, fracBitsPar, fracBitsGt1, fracBitsGt2, remRegBins, goRiceZero, goRiceParam, extendedPrecision, maxLog2TrDynamicRange );
rateIncUp [ uiBlkPos ] = xGetICRate( uiLevel+1, fracBitsPar, fracBitsGt1, fracBitsGt2, remRegBins, goRiceZero, goRiceParam, extendedPrecision, maxLog2TrDynamicRange ) - rateNow;
rateIncDown [ uiBlkPos ] = xGetICRate( uiLevel-1, fracBitsPar, fracBitsGt1, fracBitsGt2, remRegBins, goRiceZero, goRiceParam, extendedPrecision, maxLog2TrDynamicRange ) - rateNow;
}
else // uiLevel == 0
{
if( remRegBins < 4 )
{
int rateNow = xGetICRate( uiLevel, fracBitsPar, fracBitsGt1, fracBitsGt2, remRegBins, goRiceZero, goRiceParam, extendedPrecision, maxLog2TrDynamicRange );
rateIncUp [ uiBlkPos ] = xGetICRate( uiLevel+1, fracBitsPar, fracBitsGt1, fracBitsGt2, remRegBins, goRiceZero, goRiceParam, extendedPrecision, maxLog2TrDynamicRange ) - rateNow;
}
else
{
rateIncUp [ uiBlkPos ] = fracBitsGt1.intBits[ 0 ];
}
}
piDstCoeff[ uiBlkPos ] = uiLevel;//重新存储最优量化系数
d64BaseCost += pdCostCoeff [ iScanPos ];//记录cost
if( ( (iScanPos & iCGSizeM1) == 0 ) && ( iScanPos > 0 ) )
{
goRiceParam = 0;
}
else if( remRegBins >= 4 )
{
int sumAll = cctx.templateAbsSum(iScanPos, piDstCoeff, 4);//根据其右下角相邻五个系数之和选择rice参数
goRiceParam = g_auiGoRiceParsCoeff[sumAll];//得到rice参数,编码时使用
remRegBins -= (uiLevel < 2 ? uiLevel : 3) + (iScanPos != iLastScanPos);
}
}
else//(iLastScanPos < 0)
{
d64BaseCost += pdCostCoeff0[ iScanPos ];//直接使用预量化值做为最优level,记录rdcost
}
rdStats.d64SigCost += pdCostSig[ iScanPos ];
if (iScanPosinCG == 0 )
{
rdStats.d64SigCost_0 = pdCostSig[ iScanPos ];//存储最后一个系数的的rdcost
}
if (piDstCoeff[ uiBlkPos ] )
{
cctx.setSigGroup();
rdStats.d64CodedLevelandDist += pdCostCoeff[ iScanPos ] - pdCostSig[ iScanPos ];
rdStats.d64UncodedDist += pdCostCoeff0[ iScanPos ];
if ( iScanPosinCG != 0 )
{
rdStats.iNNZbeforePos0++;
}
}
} //end for (iScanPosinCG)
//判断是否要将CG量化为全零CG
if (iCGLastScanPos >= 0)
{
if( cctx.subSetId() )
{
if( !cctx.isSigGroup() )
{
const BinFracBits fracBitsSigGroup = fracBits.getFracBitsArray( cctx.sigGroupCtxId() );
d64BaseCost += xGetRateSigCoeffGroup(fracBitsSigGroup, 0) - rdStats.d64SigCost;
pdCostCoeffGroupSig[ cctx.subSetId() ] = xGetRateSigCoeffGroup(fracBitsSigGroup, 0);
}
else
{
if (cctx.subSetId() < iCGLastScanPos) //skip the last coefficient group, which will be handled together with last position below.
{
if ( rdStats.iNNZbeforePos0 == 0 )
{
d64BaseCost -= rdStats.d64SigCost_0;
rdStats.d64SigCost -= rdStats.d64SigCost_0;
}
// rd-cost if SigCoeffGroupFlag = 0, initialization
double d64CostZeroCG = d64BaseCost;
const BinFracBits fracBitsSigGroup = fracBits.getFracBitsArray( cctx.sigGroupCtxId() );
if (cctx.subSetId() < iCGLastScanPos)
{
d64BaseCost += xGetRateSigCoeffGroup(fracBitsSigGroup,1);
d64CostZeroCG += xGetRateSigCoeffGroup(fracBitsSigGroup,0);
pdCostCoeffGroupSig[ cctx.subSetId() ] = xGetRateSigCoeffGroup(fracBitsSigGroup,1);
}
// try to convert the current coeff group from non-zero to all-zero
d64CostZeroCG += rdStats.d64UncodedDist; // distortion for resetting non-zero levels to zero levels
d64CostZeroCG -= rdStats.d64CodedLevelandDist; // distortion and level cost for keeping all non-zero levels
d64CostZeroCG -= rdStats.d64SigCost; // sig cost for all coeffs, including zero levels and non-zerl levels
// if we can save cost, change this block to all-zero block
if ( d64CostZeroCG < d64BaseCost )
{
cctx.resetSigGroup();
d64BaseCost = d64CostZeroCG;
if (cctx.subSetId() < iCGLastScanPos)
{
pdCostCoeffGroupSig[ cctx.subSetId() ] = xGetRateSigCoeffGroup(fracBitsSigGroup,0);
}
// reset coeffs to 0 in this block
for( int iScanPosinCG = maxNonZeroPosInCG; iScanPosinCG >= 0; iScanPosinCG-- )
{
iScanPos = cctx.minSubPos() + iScanPosinCG;
uint32_t uiBlkPos = cctx.blockPos( iScanPos );
if (piDstCoeff[ uiBlkPos ])
{
piDstCoeff [ uiBlkPos ] = 0;
pdCostCoeff[ iScanPos ] = pdCostCoeff0[ iScanPos ];
pdCostSig [ iScanPos ] = 0;
}
}
} // end if ( d64CostAllZeros < d64BaseCost )
}
} // end if if (uiSigCoeffGroupFlag[ uiCGBlkPos ] == 0)
}
else
{
cctx.setSigGroup();
}
}
} //end for (cctx.subSetId)
//===== estimate last position =====
//对于非零系数组,找到rdcost最小的一个非零系数,将其他位置系数强制为0
if ( iLastScanPos < 0 )
{
return;
}
double d64BestCost = 0;
int iBestLastIdxP1 = 0;
if( !CU::isIntra( *tu.cu ) && isLuma( compID ) && tu.depth == 0 )
{
const BinFracBits fracBitsQtRootCbf = fracBits.getFracBitsArray( Ctx::QtRootCbf() );
d64BestCost = d64BlockUncodedCost + xGetICost( fracBitsQtRootCbf.intBits[ 0 ] );
d64BaseCost += xGetICost( fracBitsQtRootCbf.intBits[ 1 ] );
}
else
{
bool previousCbf = tu.cbf[COMPONENT_Cb];
bool lastCbfIsInferred = false;
if( useIntraSubPartitions )
{
bool rootCbfSoFar = false;
bool isLastSubPartition = CU::isISPLast(*tu.cu, tu.Y(), compID);
uint32_t nTus = tu.cu->ispMode == HOR_INTRA_SUBPARTITIONS ? tu.cu->lheight() >> floorLog2(tu.lheight()) : tu.cu->lwidth() >> floorLog2(tu.lwidth());
if( isLastSubPartition )
{
TransformUnit* tuPointer = tu.cu->firstTU;
for( int tuIdx = 0; tuIdx < nTus - 1; tuIdx++ )
{
rootCbfSoFar |= TU::getCbfAtDepth(*tuPointer, COMPONENT_Y, tu.depth);
tuPointer = tuPointer->next;
}
if( !rootCbfSoFar )
{
lastCbfIsInferred = true;
}
}
if( !lastCbfIsInferred )
{
previousCbf = TU::getPrevTuCbfAtDepth(tu, compID, tu.depth);
}
}
BinFracBits fracBitsQtCbf = fracBits.getFracBitsArray( Ctx::QtCbf[compID]( DeriveCtx::CtxQtCbf( rect.compID, previousCbf, useIntraSubPartitions ) ) );
if( !lastCbfIsInferred )
{
d64BestCost = d64BlockUncodedCost + xGetICost(fracBitsQtCbf.intBits[0]);
d64BaseCost += xGetICost(fracBitsQtCbf.intBits[1]);
}
else
{
d64BestCost = d64BlockUncodedCost;
}
}
//确定最后一个系数所在位置,若非最后一个系数的rdcost最小,则认为该点为最后一个非零系数
int lastBitsX[LAST_SIGNIFICANT_GROUPS] = { 0 };
int lastBitsY[LAST_SIGNIFICANT_GROUPS] = { 0 };
{
int dim1 = std::min<int>(JVET_C0024_ZERO_OUT_TH, uiWidth);
int dim2 = std::min<int>(JVET_C0024_ZERO_OUT_TH, uiHeight);
int bitsX = 0;
int bitsY = 0;
int ctxId;
//X-coordinate,编码最后一个系数x坐标用多少比特
for ( ctxId = 0; ctxId < g_uiGroupIdx[dim1-1]; ctxId++)
{
const BinFracBits fB = fracBits.getFracBitsArray( cctx.lastXCtxId(ctxId) );
lastBitsX[ ctxId ] = bitsX + fB.intBits[ 0 ];
bitsX += fB.intBits[ 1 ];
}
lastBitsX[ctxId] = bitsX;
//Y-coordinate,编码最后一个系数y坐标用多少比特
for ( ctxId = 0; ctxId < g_uiGroupIdx[dim2-1]; ctxId++)
{
const BinFracBits fB = fracBits.getFracBitsArray( cctx.lastYCtxId(ctxId) );
lastBitsY[ ctxId ] = bitsY + fB.intBits[ 0 ];
bitsY += fB.intBits[ 1 ];
}
lastBitsY[ctxId] = bitsY;
}
bool bFoundLast = false;
for (int iCGScanPos = iCGLastScanPos; iCGScanPos >= 0; iCGScanPos--)
{
d64BaseCost -= pdCostCoeffGroupSig [ iCGScanPos ];
if (cctx.isSigGroup( iCGScanPos ) )
{
uint32_t maxNonZeroPosInCG = iCGSizeM1;
if( lfnstIdx > 0 && ( ( uiWidth == 4 && uiHeight == 4 ) || ( uiWidth == 8 && uiHeight == 8 && cctx.cgPosX() == 0 && cctx.cgPosY() == 0 ) ) )
{
maxNonZeroPosInCG = 7;
}
for( int iScanPosinCG = maxNonZeroPosInCG; iScanPosinCG >= 0; iScanPosinCG-- )
{
iScanPos = iCGScanPos * (iCGSizeM1 + 1) + iScanPosinCG;
if (iScanPos > iLastScanPos)
{
continue;
}
uint32_t uiBlkPos = cctx.blockPos( iScanPos );
if( piDstCoeff[ uiBlkPos ] )
{
uint32_t uiPosY = uiBlkPos >> uiLog2BlockWidth;
uint32_t uiPosX = uiBlkPos - ( uiPosY << uiLog2BlockWidth );
double d64CostLast = xGetRateLast( lastBitsX, lastBitsY, uiPosX, uiPosY );
double totalCost = d64BaseCost + d64CostLast - pdCostSig[ iScanPos ];
if( totalCost < d64BestCost )
{
iBestLastIdxP1 = iScanPos + 1;
d64BestCost = totalCost;
}
if( piDstCoeff[ uiBlkPos ] > 1 )
{
bFoundLast = true;
break;
}
d64BaseCost -= pdCostCoeff[ iScanPos ];
d64BaseCost += pdCostCoeff0[ iScanPos ];
}
else
{
d64BaseCost -= pdCostSig[ iScanPos ];
}
} //end for
if (bFoundLast)
{
break;
}
} // end if (uiSigCoeffGroupFlag[ uiCGBlkPos ])
DTRACE( g_trace_ctx, D_RDOQ_COST, "%d: %3d, %3d, %dx%d, comp=%d\n", DTRACE_GET_COUNTER( g_trace_ctx, D_RDOQ_COST ), rect.x, rect.y, rect.width, rect.height, compID );
DTRACE( g_trace_ctx, D_RDOQ_COST, "Uncoded=%d\n", (int64_t)( d64BlockUncodedCost ) );
DTRACE( g_trace_ctx, D_RDOQ_COST, "Coded =%d\n", (int64_t)( d64BaseCost ) );
} // end for
//存储最优非零系数之前的值
for ( int scanPos = 0; scanPos < iBestLastIdxP1; scanPos++ )
{
int blkPos = cctx.blockPos( scanPos );
TCoeff level = piDstCoeff[ blkPos ];
uiAbsSum += level;
piDstCoeff[ blkPos ] = ( plSrcCoeff[ blkPos ] < 0 ) ? -level : level;
}
//===== clean uncoded coefficients =====
//把最优最后一个非零系数之后的值归零
for ( int scanPos = iBestLastIdxP1; scanPos <= iLastScanPos; scanPos++ )
{
piDstCoeff[ cctx.blockPos( scanPos ) ] = 0;
}
if( cctx.signHiding() && uiAbsSum>=2)
{
const double inverseQuantScale = double(g_invQuantScales[0][cQP.rem(isTransformSkip)]);
int64_t rdFactor = (int64_t)(inverseQuantScale * inverseQuantScale * (1 << (2 * cQP.per(isTransformSkip))) / m_dLambda / 16
/ (1 << (2 * DISTORTION_PRECISION_ADJUSTMENT(channelBitDepth)))
+ 0.5);
int lastCG = -1;
int absSum = 0 ;
int n ;
for (int subSet = iCGNum - 1; subSet >= 0; subSet--)
{
int subPos = subSet << cctx.log2CGSize();
int firstNZPosInCG = iCGSizeM1 + 1, lastNZPosInCG = -1;
absSum = 0 ;
for( n = iCGSizeM1; n >= 0; --n )
{
if( piDstCoeff[ cctx.blockPos( n + subPos )] )
{
lastNZPosInCG = n;
break;
}
}
for( n = 0; n <= iCGSizeM1; n++ )
{
if( piDstCoeff[ cctx.blockPos( n + subPos )] )
{
firstNZPosInCG = n;
break;
}
}
for( n = firstNZPosInCG; n <= lastNZPosInCG; n++ )
{
absSum += int(piDstCoeff[ cctx.blockPos( n + subPos )]);
}
if(lastNZPosInCG>=0 && lastCG==-1)
{
lastCG = 1;
}
if( lastNZPosInCG-firstNZPosInCG>=SBH_THRESHOLD )
{
uint32_t signbit = (piDstCoeff[cctx.blockPos(subPos+firstNZPosInCG)]>0?0:1);
if( signbit!=(absSum&0x1) ) // hide but need tune
{
// calculate the cost
int64_t minCostInc = std::numeric_limits<int64_t>::max(), curCost = std::numeric_limits<int64_t>::max();
int minPos = -1, finalChange = 0, curChange = 0;
for( n = (lastCG == 1 ? lastNZPosInCG : iCGSizeM1); n >= 0; --n )
{
uint32_t uiBlkPos = cctx.blockPos( n + subPos );
if(piDstCoeff[ uiBlkPos ] != 0 )
{
int64_t costUp = rdFactor * ( - deltaU[uiBlkPos] ) + rateIncUp[uiBlkPos];
int64_t costDown = rdFactor * ( deltaU[uiBlkPos] ) + rateIncDown[uiBlkPos]
- ((abs(piDstCoeff[uiBlkPos]) == 1) ? sigRateDelta[uiBlkPos] : 0);
if(lastCG==1 && lastNZPosInCG==n && abs(piDstCoeff[uiBlkPos])==1)
{
costDown -= (4<<SCALE_BITS);
}
if(costUp<costDown)
{
curCost = costUp;
curChange = 1;
}
else
{
curChange = -1;
if(n==firstNZPosInCG && abs(piDstCoeff[uiBlkPos])==1)
{
curCost = std::numeric_limits<int64_t>::max();
}
else
{
curCost = costDown;
}
}
}
else
{
curCost = rdFactor * ( - (abs(deltaU[uiBlkPos])) ) + (1<<SCALE_BITS) + rateIncUp[uiBlkPos] + sigRateDelta[uiBlkPos] ;
curChange = 1 ;
if(n<firstNZPosInCG)
{
uint32_t thissignbit = (plSrcCoeff[uiBlkPos]>=0?0:1);
if(thissignbit != signbit )
{
curCost = std::numeric_limits<int64_t>::max();
}
}
}
if( curCost<minCostInc)
{
minCostInc = curCost;
finalChange = curChange;
minPos = uiBlkPos;
}
}
if(piDstCoeff[minPos] == entropyCodingMaximum || piDstCoeff[minPos] == entropyCodingMinimum)
{
finalChange = -1;
}
if(plSrcCoeff[minPos]>=0)
{
piDstCoeff[minPos] += finalChange ;
}
else
{
piDstCoeff[minPos] -= finalChange ;
}
}
}
if(lastCG==1)
{
lastCG=0 ;
}
}
}
}