[x265] [PATCH] [REVIEW PATCH]Use qp value of encoded CU, instead slice qp value
Ashok Kumar Mishra
ashok at multicorewareinc.com
Wed Mar 9 15:51:57 CET 2016
Below are some test results after using the same qp for encoding the CU and
SAO distortion calculation.
*Before(crowd_run_2160p50, preset - medium, --bitrate 9000)*
encoded 500 frames in 262.47s (1.90 fps), 8956.57 kb/s, Avg QP:43.43,
Global PSNR: 30.941, SSIM Mean Y: 0.7714149 ( 6.410 dB)
*After*
encoded 500 frames in 270.96s (1.85 fps), 8954.41 kb/s, Avg QP:43.43,
Global PSNR: 30.978, SSIM Mean Y: 0.7734143 ( 6.448 dB)
--------------------------------------------------------
*Before(crowd_run_1080p50, preset - medium)*
encoded 500 frames in 81.79s (6.11 fps), 9694.14 kb/s, Avg QP:37.79,
Global PSNR: 31.037, SSIM Mean Y: 0.8414618 ( 7.999 dB)
*After*
encoded 500 frames in 81.04s (6.17 fps), 9686.80 kb/s, Avg QP:37.79,
Global PSNR: 31.044, SSIM Mean Y: 0.8417730 ( 8.007 dB)
-----------------------------------------------
*Before(**crowd_run_1080p50, preset - **veryslow)*
encoded 500 frames in 993.57s (0.50 fps), 9519.62 kb/s, Avg QP:37.78,
Global PSNR: 31.498, SSIM Mean Y: 0.8494004 ( 8.222 dB)
*After*
encoded 500 frames in 1000.08s (0.50 fps), 9511.11 kb/s, Avg QP:37.78,
Global PSNR: 31.503, SSIM Mean Y: 0.8496846 ( 8.230 dB)
------------------------------------------------
*Before(medium, crowd_run_1080p50, --bitrate 7000)*
encoded 500 frames in 78.54s (6.37 fps), 6949.02 kb/s, Avg QP:39.77,
Global PSNR: 29.962, SSIM Mean Y: 0.8069742 ( 7.144 dB)
* After*
encoded 500 frames in 75.58s (6.62 fps), 6950.09 kb/s, Avg QP:39.76,
Global PSNR: 29.973, SSIM Mean Y: 0.8075229 ( 7.156 dB)
-------------------------------------------------
*Before(veryslow, crowd_run_1080p50, --bitrate 7000)*
Before
encoded 500 frames in 864.42s (0.58 fps), 6945.49 kb/s, Avg QP:39.73,
Global PSNR: 30.418, SSIM Mean Y: 0.8157191 ( 7.345 dB)
After
encoded 500 frames in 860.32s (0.58 fps), 6945.18 kb/s, Avg QP:39.73,
Global PSNR: 30.429, SSIM Mean Y: 0.8160904 ( 7.354 dB)
On Wed, Mar 9, 2016 at 8:11 PM, <ashok at multicorewareinc.com> wrote:
> # HG changeset patch
> # User Ashok Kumar Mishra<ashok at multicorewareinc.com>
> # Date 1457424244 -19800
> # Tue Mar 08 13:34:04 2016 +0530
> # Node ID 047095eba0a40f2298df74c37abae7a2e31f4bce
> # Parent 88aebc166fa8e16f91d5f0acce77690003be9d91
> [REVIEW PATCH]Use qp value of encoded CU, instead slice qp value
> When dqp is enabled, qp value applied on CU for encoding is different from
> slice qp. So in this case the slice qp value
> should not be used for SAO offset distortion calculation. That means the
> same qp value used for encoding CU must be used
> for SAO offset distortion calculation.
>
> diff -r 88aebc166fa8 -r 047095eba0a4 source/encoder/frameencoder.cpp
> --- a/source/encoder/frameencoder.cpp Fri Mar 04 16:59:45 2016 +0530
> +++ b/source/encoder/frameencoder.cpp Tue Mar 08 13:34:04 2016 +0530
> @@ -439,7 +439,7 @@
>
> m_initSliceContext.resetEntropy(*slice);
>
> - m_frameFilter.start(m_frame, m_initSliceContext, qp);
> + m_frameFilter.start(m_frame, m_initSliceContext);
>
> /* ensure all rows are blocked prior to initializing row CTU counters
> */
> WaveFront::clearEnabledRowMask();
> diff -r 88aebc166fa8 -r 047095eba0a4 source/encoder/framefilter.cpp
> --- a/source/encoder/framefilter.cpp Fri Mar 04 16:59:45 2016 +0530
> +++ b/source/encoder/framefilter.cpp Tue Mar 08 13:34:04 2016 +0530
> @@ -103,7 +103,7 @@
>
> }
>
> -void FrameFilter::start(Frame *frame, Entropy& initState, int qp)
> +void FrameFilter::start(Frame *frame, Entropy& initState)
> {
> m_frame = frame;
>
> @@ -113,7 +113,7 @@
> for(int row = 0; row < m_numRows; row++)
> {
> if (m_param->bEnableSAO)
> - m_parallelFilter[row].m_sao.startSlice(frame, initState,
> qp);
> + m_parallelFilter[row].m_sao.startSlice(frame, initState);
>
> m_parallelFilter[row].m_lastCol.set(0);
> m_parallelFilter[row].m_allowedCol.set(0);
> diff -r 88aebc166fa8 -r 047095eba0a4 source/encoder/framefilter.h
> --- a/source/encoder/framefilter.h Fri Mar 04 16:59:45 2016 +0530
> +++ b/source/encoder/framefilter.h Tue Mar 08 13:34:04 2016 +0530
> @@ -127,7 +127,7 @@
> void init(Encoder *top, FrameEncoder *frame, int numRows, uint32_t
> numCols);
> void destroy();
>
> - void start(Frame *pic, Entropy& initState, int qp);
> + void start(Frame *pic, Entropy& initState);
>
> void processRow(int row);
> void processPostRow(int row);
> diff -r 88aebc166fa8 -r 047095eba0a4 source/encoder/sao.cpp
> --- a/source/encoder/sao.cpp Fri Mar 04 16:59:45 2016 +0530
> +++ b/source/encoder/sao.cpp Tue Mar 08 13:34:04 2016 +0530
> @@ -76,8 +76,6 @@
> m_countPreDblk = NULL;
> m_offsetOrgPreDblk = NULL;
> m_refDepth = 0;
> - m_lumaLambda = 0;
> - m_chromaLambda = 0;
> m_param = NULL;
> m_clipTable = NULL;
> m_clipTableBase = NULL;
> @@ -226,17 +224,10 @@
> saoParam->ctuParam[i] = new SaoCtuParam[m_numCuInHeight *
> m_numCuInWidth];
> }
>
> -void SAO::startSlice(Frame* frame, Entropy& initState, int qp)
> +void SAO::startSlice(Frame* frame, Entropy& initState)
> {
> - Slice* slice = frame->m_encData->m_slice;
> - int qpCb = qp;
> - if (m_param->internalCsp == X265_CSP_I420)
> - qpCb = x265_clip3(QP_MIN, QP_MAX_MAX, (int)g_chromaScale[qp +
> slice->m_pps->chromaQpOffset[0]]);
> - else
> - qpCb = X265_MIN(qp + slice->m_pps->chromaQpOffset[0],
> QP_MAX_SPEC);
> - m_lumaLambda = x265_lambda2_tab[qp];
> - m_chromaLambda = x265_lambda2_tab[qpCb]; // Use Cb QP for SAO chroma
> m_frame = frame;
> + Slice* slice = m_frame->m_encData->m_slice;
>
> switch (slice->m_sliceType)
> {
> @@ -1197,7 +1188,22 @@
>
> void SAO::rdoSaoUnitCu(SAOParam* saoParam, int rowBaseAddr, int idxX, int
> addr)
> {
> - double lambda[3] = {m_lumaLambda, m_chromaLambda, m_chromaLambda};
> + Slice* slice = m_frame->m_encData->m_slice;
> +// int qp = slice->m_sliceQp;
> + const CUData* cu = m_frame->m_encData->getPicCTU(addr);
> + int qp = cu->m_qp[0];
> +
> + double lambda[2] = {0.0};
> +
> + int qpCb = qp;
> + if (m_param->internalCsp == X265_CSP_I420)
> + qpCb = x265_clip3(QP_MIN, QP_MAX_MAX, (int)g_chromaScale[qp +
> slice->m_pps->chromaQpOffset[0]]);
> + else
> + qpCb = X265_MIN(qp + slice->m_pps->chromaQpOffset[0],
> QP_MAX_SPEC);
> +
> + lambda[0] = x265_lambda2_tab[qp];
> + lambda[1] = x265_lambda2_tab[qpCb]; // Use Cb QP for SAO chroma
> +
> const bool allowMerge[2] = {(idxX != 0), (rowBaseAddr != 0)}; //
> left, up
>
> const int addrMerge[2] = {(idxX ? addr - 1 : -1), (rowBaseAddr ? addr
> - m_numCuInWidth : -1)};// left, up
> @@ -1242,9 +1248,9 @@
> saoStatsInitialOffset(chroma);
>
> double mergeDist[NUM_MERGE_MODE] = { 0.0 };
> - saoLumaComponentParamDist(saoParam, addr, mergeDist);
> + saoLumaComponentParamDist(saoParam, addr, mergeDist, lambda);
> if (chroma)
> - saoChromaComponentParamDist(saoParam, addr, mergeDist);
> + saoChromaComponentParamDist(saoParam, addr, mergeDist, lambda);
>
> if (saoParam->bSaoFlag[0] || saoParam->bSaoFlag[1])
> {
> @@ -1286,10 +1292,9 @@
> }
> }
>
> - mergeDist[mergeIdx + 1] += ((double)estDist /
> lambda[plane]);
> + mergeDist[mergeIdx + 1] += ((double)estDist /
> lambda[!!plane]);
> }
>
> -
> m_entropyCoder.load(m_rdContexts.cur);
> m_entropyCoder.resetBits();
> if (allowMerge[0])
> @@ -1412,7 +1417,7 @@
> return bestOffset;
> }
>
> -void SAO::saoLumaComponentParamDist(SAOParam* saoParam, int addr, double*
> mergeDist)
> +void SAO::saoLumaComponentParamDist(SAOParam* saoParam, int addr, double*
> mergeDist, double* lambda)
> {
> int64_t bestDist = 0;
> int bestTypeIdx = -1;
> @@ -1426,7 +1431,7 @@
> m_entropyCoder.resetBits();
> m_entropyCoder.codeSaoType(0);
>
> - double dCostPartBest = m_entropyCoder.getNumberOfWrittenBits() *
> m_lumaLambda;
> + double dCostPartBest = m_entropyCoder.getNumberOfWrittenBits() *
> lambda[0];
>
> //EO distortion calculation
> for (int typeIdx = 0; typeIdx < MAX_NUM_SAO_TYPE - 1; typeIdx++)
> @@ -1439,7 +1444,7 @@
> int32_t& offsetOut = m_offset[0][typeIdx][classIdx];
>
> if (count)
> - offsetOut = estIterOffset(typeIdx, m_lumaLambda,
> offsetOut, count, offsetOrg, distBOClasses[0], costBOClasses[0]);
> + offsetOut = estIterOffset(typeIdx, lambda[0], offsetOut,
> count, offsetOrg, distBOClasses[0], costBOClasses[0]);
> else
> offsetOut = 0;
>
> @@ -1451,7 +1456,7 @@
> m_entropyCoder.codeSaoOffsetEO(m_offset[0][typeIdx] + 1, typeIdx,
> 0);
>
> uint32_t estRate = m_entropyCoder.getNumberOfWrittenBits();
> - double cost = (double)estDist + m_lumaLambda * (double)estRate;
> + double cost = (double)estDist + lambda[0] * (double)estRate;
>
> if (cost < dCostPartBest)
> {
> @@ -1479,10 +1484,10 @@
> int32_t& offsetOut = m_offset[0][SAO_BO][classIdx];
>
> distBOClasses[classIdx] = 0;
> - costBOClasses[classIdx] = m_lumaLambda;
> + costBOClasses[classIdx] = lambda[0];
>
> if (count)
> - offsetOut = estIterOffset(SAO_BO, m_lumaLambda, offsetOut,
> count, offsetOrg, distBOClasses[classIdx], costBOClasses[classIdx]);
> + offsetOut = estIterOffset(SAO_BO, lambda[0], offsetOut,
> count, offsetOrg, distBOClasses[classIdx], costBOClasses[classIdx]);
> else
> offsetOut = 0;
> }
> @@ -1513,7 +1518,7 @@
> m_entropyCoder.codeSaoOffsetBO(m_offset[0][SAO_BO] + bestClassBO,
> bestClassBO, 0);
>
> uint32_t estRate = m_entropyCoder.getNumberOfWrittenBits();
> - double cost = (double)estDist + m_lumaLambda * (double)estRate;
> + double cost = (double)estDist + lambda[0] * (double)estRate;
>
> if (cost < dCostPartBest)
> {
> @@ -1527,13 +1532,13 @@
> lclCtuParam->offset[classIdx] =
> (int)m_offset[0][SAO_BO][classIdx + bestClassBO];
> }
>
> - mergeDist[0] = ((double)bestDist / m_lumaLambda);
> + mergeDist[0] = ((double)bestDist / lambda[0]);
> m_entropyCoder.load(m_rdContexts.temp);
> m_entropyCoder.codeSaoOffset(*lclCtuParam, 0);
> m_entropyCoder.store(m_rdContexts.temp);
> }
>
> -void SAO::saoChromaComponentParamDist(SAOParam* saoParam, int addr,
> double* mergeDist)
> +void SAO::saoChromaComponentParamDist(SAOParam* saoParam, int addr,
> double* mergeDist, double* lambda)
> {
> int64_t bestDist = 0;
> int bestTypeIdx = -1;
> @@ -1548,7 +1553,7 @@
> m_entropyCoder.resetBits();
> m_entropyCoder.codeSaoType(0);
>
> - double costPartBest = m_entropyCoder.getNumberOfWrittenBits() *
> m_chromaLambda;
> + double costPartBest = m_entropyCoder.getNumberOfWrittenBits() *
> lambda[1];
>
> //EO RDO
> for (int typeIdx = 0; typeIdx < MAX_NUM_SAO_TYPE - 1; typeIdx++)
> @@ -1563,7 +1568,7 @@
> int32_t& offsetOut = m_offset[compIdx][typeIdx][classIdx];
>
> if (count)
> - offsetOut = estIterOffset(typeIdx, m_chromaLambda,
> offsetOut, count, offsetOrg, distBOClasses[0], costBOClasses[0]);
> + offsetOut = estIterOffset(typeIdx, lambda[1],
> offsetOut, count, offsetOrg, distBOClasses[0], costBOClasses[0]);
> else
> offsetOut = 0;
>
> @@ -1578,7 +1583,7 @@
> m_entropyCoder.codeSaoOffsetEO(m_offset[compIdx + 1][typeIdx]
> + 1, typeIdx, compIdx + 1);
>
> uint32_t estRate = m_entropyCoder.getNumberOfWrittenBits();
> - double cost = (double)(estDist[0] + estDist[1]) + m_chromaLambda
> * (double)estRate;
> + double cost = (double)(estDist[0] + estDist[1]) + lambda[1] *
> (double)estRate;
>
> if (cost < costPartBest)
> {
> @@ -1615,10 +1620,10 @@
> int32_t& offsetOut = m_offset[compIdx][SAO_BO][classIdx];
>
> distBOClasses[classIdx] = 0;
> - costBOClasses[classIdx] = m_chromaLambda;
> + costBOClasses[classIdx] = lambda[1];
>
> if (count)
> - offsetOut = estIterOffset(SAO_BO, m_chromaLambda,
> offsetOut, count, offsetOrg, distBOClasses[classIdx],
> costBOClasses[classIdx]);
> + offsetOut = estIterOffset(SAO_BO, lambda[1], offsetOut,
> count, offsetOrg, distBOClasses[classIdx], costBOClasses[classIdx]);
> else
> offsetOut = 0;
> }
> @@ -1648,7 +1653,7 @@
> m_entropyCoder.codeSaoOffsetBO(m_offset[compIdx + 1][SAO_BO] +
> bestClassBO[compIdx], bestClassBO[compIdx], compIdx + 1);
>
> uint32_t estRate = m_entropyCoder.getNumberOfWrittenBits();
> - double cost = (double)(estDist[0] + estDist[1]) + m_chromaLambda *
> (double)estRate;
> + double cost = (double)(estDist[0] + estDist[1]) + lambda[1] *
> (double)estRate;
>
> if (cost < costPartBest)
> {
> @@ -1665,7 +1670,7 @@
> }
> }
>
> - mergeDist[0] += ((double)bestDist / m_chromaLambda);
> + mergeDist[0] += ((double)bestDist / lambda[1]);
> m_entropyCoder.load(m_rdContexts.temp);
> m_entropyCoder.codeSaoOffset(*lclCtuParam[0], 1);
> m_entropyCoder.codeSaoOffset(*lclCtuParam[1], 2);
> diff -r 88aebc166fa8 -r 047095eba0a4 source/encoder/sao.h
> --- a/source/encoder/sao.h Fri Mar 04 16:59:45 2016 +0530
> +++ b/source/encoder/sao.h Tue Mar 08 13:34:04 2016 +0530
> @@ -114,10 +114,6 @@
> int m_refDepth;
> int m_numNoSao[2];
>
> - double m_lumaLambda;
> - double m_chromaLambda;
> - /* TODO: No doubles for distortion */
> -
> SAO();
>
> bool create(x265_param* param, int initCommon);
> @@ -126,7 +122,7 @@
>
> void allocSaoParam(SAOParam* saoParam) const;
>
> - void startSlice(Frame* pic, Entropy& initState, int qp);
> + void startSlice(Frame* pic, Entropy& initState);
> void resetStats();
>
> // CTU-based SAO process without slice granularity
> @@ -138,8 +134,8 @@
> void calcSaoStatsCu(int addr, int plane);
> void calcSaoStatsCu_BeforeDblk(Frame* pic, int idxX, int idxY);
>
> - void saoLumaComponentParamDist(SAOParam* saoParam, int addr, double*
> mergeDist);
> - void saoChromaComponentParamDist(SAOParam* saoParam, int addr,
> double* mergeDist);
> + void saoLumaComponentParamDist(SAOParam* saoParam, int addr, double*
> mergeDist, double* lambda);
> + void saoChromaComponentParamDist(SAOParam* saoParam, int addr,
> double* mergeDist, double* lambda);
>
> inline int estIterOffset(int typeIdx, double lambda, int offset,
> int32_t count, int32_t offsetOrg,
> int& currentDistortionTableBo, double&
> currentRdCostTableBo);
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mailman.videolan.org/pipermail/x265-devel/attachments/20160309/a1d454b8/attachment-0001.html>
More information about the x265-devel
mailing list