Why would rskip=2 not work on rd > 4? Is there a technical reason, or is there an implicit assumption that the users won't want to use rskip at rd > 4?
On Wed, Jan 22, 2020, 04:00 Kavitha Sampath <kavi...@multicorewareinc.com> wrote: > > > On Tue, Jan 21, 2020 at 11:32 AM <srikanth.kurap...@multicorewareinc.com> > wrote: > >> # HG changeset patch >> # User Srikanth Kurapati >> # Date 1579584229 -19800 >> # Tue Jan 21 10:53:49 2020 +0530 >> # Node ID e0e0270ead4189a545821b00011c47d61e6b817a >> # Parent acc5d16999e2faf6e75ecc1df9a01c1953ebaf8c >> Edge Aware Quad Tree Establishment. >> >> This patch does the following: >> 1. Terminates recursion using edge information. >> 2. Adds modes for "--rskip". Modes 0,1 for current usage and 2 for edge >> based >> rskip for RD levels 0 to 4. >> 3. Adds option "edge-threshold" to decide recursion skip using CU edge >> density. >> 4. Re uses edge information when already available in encoder. >> >> diff -r acc5d16999e2 -r e0e0270ead41 doc/reST/cli.rst >> --- a/doc/reST/cli.rst Mon Jan 20 18:07:59 2020 +0530 >> +++ b/doc/reST/cli.rst Tue Jan 21 10:53:49 2020 +0530 >> @@ -842,15 +842,20 @@ >> Measure 2Nx2N merge candidates first; if no residual is found, >> additional modes at that depth are not analysed. Default disabled >> >> -.. option:: --rskip, --no-rskip >> - >> - This option determines early exit from CU depth recursion. When a >> skip CU is >> - found, additional heuristics (depending on rd-level) are used to >> decide whether >> - to terminate recursion. In rdlevels 5 and 6, comparison with >> inter2Nx2N is used, >> - while at rdlevels 4 and neighbour costs are used to skip >> recursion. >> - Provides minimal quality degradation at good performance gains >> when enabled. >> - >> - Default: enabled, disabled for :option:`--tune grain` >> +.. option:: --rskip <0|1|2> >> + >> + This option determines early exit from CU depth recursion in >> modes 1 and 2. When a skip CU is >> + found, additional heuristics (depending on RD level and rskip >> mode) are used to decide whether >> + to terminate recursion. In RD levels 5 and 6, comparison with >> inter2Nx2N is used, >> + while at RD levels 4 and below, neighbour costs are used to skip >> recursion in mode 1, and CU edge density in mode 2. >> + Provides minimal quality degradation at good performance gains >> for non-zero modes. :option:`--r-skip mode 0` means disabled. >> + >> + Default: 1, disabled when :option:`--tune grain` is used. >> + >> +.. option:: --edge-threshold <0..100> >> + >> + Denotes the minimum expected edge-density percentage within the >> CU, below which the recursion is skipped. >> + Default: 5, requires :option:`--rskip mode 2` to be enabled. >> > .. option:: --splitrd-skip, --no-splitrd-skip >> >> diff -r acc5d16999e2 -r e0e0270ead41 source/CMakeLists.txt >> --- a/source/CMakeLists.txt Mon Jan 20 18:07:59 2020 +0530 >> +++ b/source/CMakeLists.txt Tue Jan 21 10:53:49 2020 +0530 >> @@ -29,7 +29,7 @@ >> 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 188) >> +set(X265_BUILD 189) >> configure_file("${PROJECT_SOURCE_DIR}/x265.def.in" >> "${PROJECT_BINARY_DIR}/x265.def") >> configure_file("${PROJECT_SOURCE_DIR}/x265_config.h.in" >> diff -r acc5d16999e2 -r e0e0270ead41 source/common/common.h >> --- a/source/common/common.h Mon Jan 20 18:07:59 2020 +0530 >> +++ b/source/common/common.h Tue Jan 21 10:53:49 2020 +0530 >> @@ -129,6 +129,7 @@ >> typedef uint64_t sum2_t; >> typedef uint64_t pixel4; >> typedef int64_t ssum2_t; >> +#define SHIFT_TO_BITPLANE 9 >> #define HISTOGRAM_BINS 1024 >> #define SHIFT 1 >> #else >> @@ -137,6 +138,7 @@ >> typedef uint32_t sum2_t; >> typedef uint32_t pixel4; >> typedef int32_t ssum2_t; // Signed sum >> +#define SHIFT_TO_BITPLANE 7 >> #define HISTOGRAM_BINS 256 >> #define SHIFT 0 >> #endif // if HIGH_BIT_DEPTH >> @@ -272,6 +274,9 @@ >> #define MAX_TR_SIZE (1 << MAX_LOG2_TR_SIZE) >> #define MAX_TS_SIZE (1 << MAX_LOG2_TS_SIZE) >> >> +#define RDCOST_BASED_RSKIP 1 >> +#define EDGE_BASED_RSKIP 2 >> + >> #define COEF_REMAIN_BIN_REDUCTION 3 // indicates the level at which >> the VLC >> // transitions from Golomb-Rice to >> TU+EG(k) >> >> diff -r acc5d16999e2 -r e0e0270ead41 source/common/frame.cpp >> --- a/source/common/frame.cpp Mon Jan 20 18:07:59 2020 +0530 >> +++ b/source/common/frame.cpp Tue Jan 21 10:53:49 2020 +0530 >> @@ -61,6 +61,7 @@ >> m_edgePic = NULL; >> m_gaussianPic = NULL; >> m_thetaPic = NULL; >> + m_edgeBitPlane = NULL; >> } >> >> bool Frame::create(x265_param *param, float* quantOffsets) >> @@ -115,6 +116,18 @@ >> m_thetaPic = X265_MALLOC(pixel, m_stride * (maxHeight + >> (m_lumaMarginY * 2))); >> } >> >> + if (param->bEnableRecursionSkip == EDGE_BASED_RSKIP) >> + { >> + uint32_t numCuInWidth = (param->sourceWidth + param->maxCUSize - >> 1) / param->maxCUSize; >> + uint32_t numCuInHeight = (param->sourceHeight + param->maxCUSize >> - 1) / param->maxCUSize; >> + uint32_t lumaMarginX = param->maxCUSize + 32; >> + uint32_t lumaMarginY = param->maxCUSize + 16; >> + uint32_t stride = (numCuInWidth * param->maxCUSize) + >> (lumaMarginX << 1); >> + uint32_t maxHeight = numCuInHeight * param->maxCUSize; >> + m_bitPlaneSize = stride * (maxHeight + (lumaMarginY * 2)); >> + CHECKED_MALLOC_ZERO(m_edgeBitPlane, pixel, m_bitPlaneSize); >> + } >> + >> if (m_fencPic->create(param, !!m_param->bCopyPicToFrame) && >> m_lowres.create(param, m_fencPic, param->rc.qgSize)) >> { >> X265_CHECK((m_reconColCount == NULL), "m_reconColCount was >> initialized"); >> @@ -267,4 +280,9 @@ >> X265_FREE(m_gaussianPic); >> X265_FREE(m_thetaPic); >> } >> + >> + if (m_param->bEnableRecursionSkip == EDGE_BASED_RSKIP) >> + { >> + X265_FREE(m_edgeBitPlane); >> + } >> } >> diff -r acc5d16999e2 -r e0e0270ead41 source/common/frame.h >> --- a/source/common/frame.h Mon Jan 20 18:07:59 2020 +0530 >> +++ b/source/common/frame.h Tue Jan 21 10:53:49 2020 +0530 >> @@ -137,6 +137,8 @@ >> pixel* m_gaussianPic; >> pixel* m_thetaPic; >> >> + pixel* m_edgeBitPlane; >> + uint32_t m_bitPlaneSize; >> Frame(); >> >> bool create(x265_param *param, float* quantOffsets); >> diff -r acc5d16999e2 -r e0e0270ead41 source/common/param.cpp >> --- a/source/common/param.cpp Mon Jan 20 18:07:59 2020 +0530 >> +++ b/source/common/param.cpp Tue Jan 21 10:53:49 2020 +0530 >> @@ -199,6 +199,7 @@ >> param->bEnableWeightedBiPred = 0; >> param->bEnableEarlySkip = 1; >> param->bEnableRecursionSkip = 1; >> + param->edgeThreshold = 0.05f; >> > [KS] Are we going to have the same default threshold for both flows - > (a)histogram based scenecut =1 && aqmode=0 (b) histogram based scenecut =0 > && aqmode=1 > When the variance of the two flows can vary, shouldn't the thresholds vary? > [KS] The docs isn't giving much guidance to users on how to set the > threshold for each of the flows you are handling > >> param->bEnableAMP = 0; >> param->bEnableRectInter = 0; >> param->rdLevel = 3; >> @@ -702,8 +703,9 @@ >> OPT("ref") p->maxNumReferences = atoi(value); >> OPT("fast-intra") p->bEnableFastIntra = atobool(value); >> OPT("early-skip") p->bEnableEarlySkip = atobool(value); >> - OPT("rskip") p->bEnableRecursionSkip = atobool(value); >> - OPT("me")p->searchMethod = parseName(value, x265_motion_est_names, >> bError); >> + OPT("rskip") p->bEnableRecursionSkip = atoi(value); >> + OPT("edge-threshold") p->edgeThreshold = atoi(value)/100.0f; >> + OPT("me") p->searchMethod = parseName(value, x265_motion_est_names, >> bError); >> OPT("subme") p->subpelRefine = atoi(value); >> OPT("merange") p->searchRange = atoi(value); >> OPT("rect") p->bEnableRectInter = atobool(value); >> @@ -919,7 +921,7 @@ >> OPT("max-merge") p->maxNumMergeCand = (uint32_t)atoi(value); >> OPT("temporal-mvp") p->bEnableTemporalMvp = atobool(value); >> OPT("early-skip") p->bEnableEarlySkip = atobool(value); >> - OPT("rskip") p->bEnableRecursionSkip = atobool(value); >> + OPT("rskip") p->bEnableRecursionSkip = atoi(value); >> OPT("rdpenalty") p->rdPenalty = atoi(value); >> OPT("tskip") p->bEnableTransformSkip = atobool(value); >> OPT("no-tskip-fast") p->bEnableTSkipFast = atobool(value); >> @@ -1221,6 +1223,7 @@ >> } >> } >> OPT("hist-threshold") p->edgeTransitionThreshold = atof(value); >> + OPT("edge-threshold") p->edgeThreshold = atoi(value)/100.0f; >> OPT("lookahead-threads") p->lookaheadThreads = atoi(value); >> OPT("opt-cu-delta-qp") p->bOptCUDeltaQP = atobool(value); >> OPT("multi-pass-opt-analysis") p->analysisMultiPassRefine = >> atobool(value); >> @@ -1596,9 +1599,16 @@ >> CHECK(param->rdLevel < 1 || param->rdLevel > 6, >> "RD Level is out of range"); >> CHECK(param->rdoqLevel < 0 || param->rdoqLevel > 2, >> - "RDOQ Level is out of range"); >> + "RDOQ Level is out of range"); >> CHECK(param->dynamicRd < 0 || param->dynamicRd > >> x265_ADAPT_RD_STRENGTH, >> - "Dynamic RD strength must be between 0 and 4"); >> + "Dynamic RD strength must be between 0 and 4"); >> + CHECK(param->bEnableRecursionSkip > 2 || param->bEnableRecursionSkip >> < 0, >> + "Invalid Recursion skip mode. Valid modes 0,1,2"); >> + if (param->bEnableRecursionSkip == EDGE_BASED_RSKIP) >> + { >> + CHECK(param->edgeThreshold < 0.0f || param->edgeThreshold > 1.0f, >> + "Minimum edge density percentage for a CU should be an >> integer between 0 to 100"); >> + } >> CHECK(param->bframes && param->bframes >= param->lookaheadDepth && >> !param->rc.bStatRead, >> "Lookahead depth must be greater than the max consecutive >> bframe count"); >> CHECK(param->bframes < 0, >> @@ -1908,7 +1918,9 @@ >> TOOLVAL(param->psyRdoq, "psy-rdoq=%.2lf"); >> TOOLOPT(param->bEnableRdRefine, "rd-refine"); >> TOOLOPT(param->bEnableEarlySkip, "early-skip"); >> - TOOLOPT(param->bEnableRecursionSkip, "rskip"); >> + TOOLVAL(param->bEnableRecursionSkip, "rskip mode=%d"); >> + if (param->bEnableRecursionSkip == EDGE_BASED_RSKIP) >> + TOOLVAL(param->edgeThreshold, "rskip-threshold=%.2f"); >> TOOLOPT(param->bEnableSplitRdSkip, "splitrd-skip"); >> TOOLVAL(param->noiseReductionIntra, "nr-intra=%d"); >> TOOLVAL(param->noiseReductionInter, "nr-inter=%d"); >> @@ -2067,6 +2079,9 @@ >> s += sprintf(s, " selective-sao=%d", p->selectiveSAO); >> BOOL(p->bEnableEarlySkip, "early-skip"); >> BOOL(p->bEnableRecursionSkip, "rskip"); >> + if (p->bEnableRecursionSkip == EDGE_BASED_RSKIP) >> + s += sprintf(s, " edge-threshold=%f", p->edgeThreshold); >> + >> BOOL(p->bEnableFastIntra, "fast-intra"); >> BOOL(p->bEnableTSkipFast, "tskip-fast"); >> BOOL(p->bCULossless, "cu-lossless"); >> @@ -2374,6 +2389,7 @@ >> dst->rdLevel = src->rdLevel; >> dst->bEnableEarlySkip = src->bEnableEarlySkip; >> dst->bEnableRecursionSkip = src->bEnableRecursionSkip; >> + dst->edgeThreshold = src->edgeThreshold; >> dst->bEnableFastIntra = src->bEnableFastIntra; >> dst->bEnableTSkipFast = src->bEnableTSkipFast; >> dst->bCULossless = src->bCULossless; >> diff -r acc5d16999e2 -r e0e0270ead41 source/common/pixel.cpp >> --- a/source/common/pixel.cpp Mon Jan 20 18:07:59 2020 +0530 >> +++ b/source/common/pixel.cpp Tue Jan 21 10:53:49 2020 +0530 >> @@ -876,6 +876,18 @@ >> } >> } >> >> +static void planecopy_pp_shr_c(const pixel* src, intptr_t srcStride, >> pixel* dst, intptr_t dstStride, int width, int height, int shift) >> +{ >> + for (int r = 0; r < height; r++) >> + { >> + for (int c = 0; c < width; c++) >> + dst[c] = (pixel)((src[c] >> shift)); >> + >> + dst += dstStride; >> + src += srcStride; >> + } >> +} >> + >> static void planecopy_sp_shl_c(const uint16_t* src, intptr_t srcStride, >> pixel* dst, intptr_t dstStride, int width, int height, int shift, uint16_t >> mask) >> { >> for (int r = 0; r < height; r++) >> @@ -1316,6 +1328,7 @@ >> p.planecopy_cp = planecopy_cp_c; >> p.planecopy_sp = planecopy_sp_c; >> p.planecopy_sp_shl = planecopy_sp_shl_c; >> + p.planecopy_pp_shr = planecopy_pp_shr_c; >> #if HIGH_BIT_DEPTH >> p.planeClipAndMax = planeClipAndMax_c; >> #endif >> diff -r acc5d16999e2 -r e0e0270ead41 source/common/primitives.h >> --- a/source/common/primitives.h Mon Jan 20 18:07:59 2020 +0530 >> +++ b/source/common/primitives.h Tue Jan 21 10:53:49 2020 +0530 >> @@ -204,6 +204,7 @@ >> typedef void (*sign_t)(int8_t *dst, const pixel *src1, const pixel >> *src2, const int endX); >> typedef void (*planecopy_cp_t) (const uint8_t* src, intptr_t srcStride, >> pixel* dst, intptr_t dstStride, int width, int height, int shift); >> typedef void (*planecopy_sp_t) (const uint16_t* src, intptr_t srcStride, >> pixel* dst, intptr_t dstStride, int width, int height, int shift, uint16_t >> mask); >> +typedef void (*planecopy_pp_t) (const pixel* src, intptr_t srcStride, >> pixel* dst, intptr_t dstStride, int width, int height, int shift); >> typedef pixel (*planeClipAndMax_t)(pixel *src, intptr_t stride, int >> width, int height, uint64_t *outsum, const pixel minPix, const pixel >> maxPix); >> >> typedef void (*cutree_propagate_cost) (int* dst, const uint16_t* >> propagateIn, const int32_t* intraCosts, const uint16_t* interCosts, const >> int32_t* invQscales, const double* fpsFactor, int len); >> @@ -358,6 +359,7 @@ >> planecopy_cp_t planecopy_cp; >> planecopy_sp_t planecopy_sp; >> planecopy_sp_t planecopy_sp_shl; >> + planecopy_pp_t planecopy_pp_shr; >> planeClipAndMax_t planeClipAndMax; >> >> weightp_sp_t weight_sp; >> diff -r acc5d16999e2 -r e0e0270ead41 source/encoder/analysis.cpp >> --- a/source/encoder/analysis.cpp Mon Jan 20 18:07:59 2020 +0530 >> +++ b/source/encoder/analysis.cpp Tue Jan 21 10:53:49 2020 +0530 >> @@ -1317,12 +1317,19 @@ >> if (md.bestMode && m_param->bEnableRecursionSkip && >> !bCtuInfoCheck && !(m_param->bAnalysisType == AVC_INFO && >> m_param->analysisLoadReuseLevel == 7 && (m_modeFlag[0] || m_modeFlag[1]))) >> { >> skipRecursion = md.bestMode->cu.isSkipped(0); >> - if (mightSplit && depth >= minDepth && !skipRecursion) >> + if (mightSplit && !skipRecursion) >> { >> - if (depth) >> - skipRecursion = recursionDepthCheck(parentCTU, >> cuGeom, *md.bestMode); >> - if (m_bHD && !skipRecursion && m_param->rdLevel == 2 && >> md.fencYuv.m_size != MAX_CU_SIZE) >> - skipRecursion = complexityCheckCU(*md.bestMode); >> + if (depth >= minDepth && m_param->bEnableRecursionSkip >> == RDCOST_BASED_RSKIP) >> + { >> + if (depth) >> + skipRecursion = recursionDepthCheck(parentCTU, >> cuGeom, *md.bestMode); >> + if (m_bHD && !skipRecursion && m_param->rdLevel == 2 >> && md.fencYuv.m_size != MAX_CU_SIZE) >> + skipRecursion = complexityCheckCU(*md.bestMode); >> + } >> + else if (cuGeom.log2CUSize >= MAX_LOG2_CU_SIZE - 1 && >> m_param->bEnableRecursionSkip == EDGE_BASED_RSKIP) >> + { >> + skipRecursion = edgeRecursionSkip(parentCTU, cuGeom); >> + } >> } >> } >> if (m_param->bAnalysisType == AVC_INFO && md.bestMode && >> cuGeom.numPartitions <= 16 && m_param->analysisLoadReuseLevel == 7) >> @@ -3547,6 +3554,25 @@ >> return false; >> } >> >> +bool Analysis::edgeRecursionSkip(const CUData& ctu, const CUGeom& cuGeom) >> +{ >> + int blockType = cuGeom.log2CUSize - 2; >> + int shift = cuGeom.log2CUSize * 2; >> + intptr_t stride = m_frame->m_fencPic->m_stride; >> + pixel* edgePic = m_frame->m_edgeBitPlane + >> m_frame->m_fencPic->m_lumaMarginY * m_frame->m_fencPic->m_stride + >> m_frame->m_fencPic->m_lumaMarginX; >> > [KS] edgePic's address is the same for every CU in a frame. Why are you > computing this initial offset every time? > > + intptr_t blockOffsetLuma = (ctu.m_cuPelX + >> g_zscanToPelX[cuGeom.absPartIdx]) + (ctu.m_cuPelY + >> g_zscanToPelY[cuGeom.absPartIdx]) * stride; >> > [KS] luma offset computation looks complex with g_zscanToPelX /Y addition. > Any specific reason for not using bestMode's data? > > >> + uint64_t sum_ss = primitives.cu[blockType].var(edgePic + >> blockOffsetLuma, stride); >> + uint32_t sum = (uint32_t)sum_ss; >> + uint32_t ss = (uint32_t)(sum_ss >> 32); >> + uint32_t pixelCount = 1 << shift; >> + double cuEdgeVariance = (ss - ((double)sum * sum / pixelCount)) / >> pixelCount; >> + >> + if (cuEdgeVariance > (double)m_param->edgeThreshold) >> + return false; >> + else >> + return true; >> +} >> + >> uint32_t Analysis::calculateCUVariance(const CUData& ctu, const CUGeom& >> cuGeom) >> { >> uint32_t cuVariance = 0; >> @@ -3570,7 +3596,6 @@ >> cnt++; >> } >> } >> - >> return cuVariance / cnt; >> } >> >> diff -r acc5d16999e2 -r e0e0270ead41 source/encoder/analysis.h >> --- a/source/encoder/analysis.h Mon Jan 20 18:07:59 2020 +0530 >> +++ b/source/encoder/analysis.h Tue Jan 21 10:53:49 2020 +0530 >> @@ -52,7 +52,7 @@ >> splitRefs = 0; >> mvCost[0] = 0; // L0 >> mvCost[1] = 0; // L1 >> - sa8dCost = 0; >> + sa8dCost = 0; >> } >> }; >> >> @@ -120,7 +120,6 @@ >> >> Mode& compressCTU(CUData& ctu, Frame& frame, const CUGeom& cuGeom, >> const Entropy& initialContext); >> int32_t loadTUDepth(CUGeom cuGeom, CUData parentCTU); >> - >> protected: >> /* Analysis data for save/load mode, writes/reads data based on >> absPartIdx */ >> x265_analysis_inter_data* m_reuseInterDataCTU; >> @@ -192,6 +191,7 @@ >> uint32_t topSkipMinDepth(const CUData& parentCTU, const CUGeom& >> cuGeom); >> bool recursionDepthCheck(const CUData& parentCTU, const CUGeom& >> cuGeom, const Mode& bestMode); >> bool complexityCheckCU(const Mode& bestMode); >> + bool edgeRecursionSkip(const CUData& parentCTU, const CUGeom& >> cuGeom); >> >> /* generate residual and recon pixels for an entire CTU recursively >> (RD0) */ >> void encodeResidue(const CUData& parentCTU, const CUGeom& cuGeom); >> diff -r acc5d16999e2 -r e0e0270ead41 source/encoder/encoder.cpp >> --- a/source/encoder/encoder.cpp Mon Jan 20 18:07:59 2020 +0530 >> +++ b/source/encoder/encoder.cpp Tue Jan 21 10:53:49 2020 +0530 >> @@ -1343,9 +1343,9 @@ >> int32_t numBytes = m_param->sourceBitDepth > 8 ? 2 : 1; >> memset(m_edgePic, 0, bufSize * numBytes); >> >> - if (!computeEdge(m_edgePic, src, NULL, pic->width, pic->height, >> pic->width, false)) >> - { >> - x265_log(m_param, X265_LOG_ERROR, "Failed edge computation!"); >> + if (!computeEdge(m_edgePic, src, NULL, pic->width, pic->height, >> pic->width, false, 1)) >> + { >> + x265_log(m_param, X265_LOG_ERROR, "Failed to compute edge!"); >> return false; >> } >> >> @@ -1660,6 +1660,13 @@ >> } >> } >> } >> + if (m_param->bEnableRecursionSkip == EDGE_BASED_RSKIP && >> m_param->bHistBasedSceneCut) >> + { >> + pixel* src = m_edgePic; >> + pixel* edgePic = inFrame->m_edgeBitPlane + >> inFrame->m_fencPic->m_lumaMarginY * inFrame->m_fencPic->m_stride + >> inFrame->m_fencPic->m_lumaMarginX; >> + primitives.planecopy_pp_shr(src, >> inFrame->m_fencPic->m_picWidth, edgePic, inFrame->m_fencPic->m_stride, >> + inFrame->m_fencPic->m_picWidth, >> inFrame->m_fencPic->m_picHeight, 0); >> + } >> } >> else >> { >> diff -r acc5d16999e2 -r e0e0270ead41 source/encoder/frameencoder.cpp >> --- a/source/encoder/frameencoder.cpp Mon Jan 20 18:07:59 2020 +0530 >> +++ b/source/encoder/frameencoder.cpp Tue Jan 21 10:53:49 2020 +0530 >> @@ -130,7 +130,7 @@ >> { >> rowSum += sliceGroupSizeAccu; >> m_sliceBaseRow[++sidx] = i; >> - } >> + } >> } >> X265_CHECK(sidx < m_param->maxSlices, "sliceID check failed!"); >> m_sliceBaseRow[0] = 0; >> @@ -268,6 +268,20 @@ >> curFrame->m_encData->m_jobProvider = this; >> curFrame->m_encData->m_slice->m_mref = m_mref; >> >> + if (!m_param->bHistBasedSceneCut && m_param->rc.aqMode != >> X265_AQ_EDGE && m_param->bEnableRecursionSkip == EDGE_BASED_RSKIP) >> + { >> + int height = curFrame->m_fencPic->m_picHeight; >> + int width = curFrame->m_fencPic->m_picWidth; >> + intptr_t stride = curFrame->m_fencPic->m_stride; >> + pixel* edgePic = curFrame->m_edgeBitPlane + >> curFrame->m_fencPic->m_lumaMarginY * curFrame->m_fencPic->m_stride + >> curFrame->m_fencPic->m_lumaMarginX; >> + >> + if (!computeEdge(edgePic, curFrame->m_fencPic->m_picOrg[0], >> NULL, stride, height, width, false, 1)) >> + { >> + x265_log(m_param, X265_LOG_ERROR, " Failed to compute edge >> !"); >> + return false; >> + } >> + } >> + >> if (!m_cuGeoms) >> { >> if (!initializeGeoms()) >> diff -r acc5d16999e2 -r e0e0270ead41 source/encoder/slicetype.cpp >> --- a/source/encoder/slicetype.cpp Mon Jan 20 18:07:59 2020 +0530 >> +++ b/source/encoder/slicetype.cpp Tue Jan 21 10:53:49 2020 +0530 >> @@ -87,7 +87,7 @@ >> >> namespace X265_NS { >> >> -bool computeEdge(pixel *edgePic, pixel *refPic, pixel *edgeTheta, >> intptr_t stride, int height, int width, bool bcalcTheta) >> +bool computeEdge(pixel* edgePic, pixel* refPic, pixel* edgeTheta, >> intptr_t stride, int height, int width, bool bcalcTheta, pixel whitePixel) >> { >> intptr_t rowOne = 0, rowTwo = 0, rowThree = 0, colOne = 0, colTwo = >> 0, colThree = 0; >> intptr_t middle = 0, topLeft = 0, topRight = 0, bottomLeft = 0, >> bottomRight = 0; >> @@ -141,7 +141,7 @@ >> theta = 180 + theta; >> edgeTheta[middle] = (pixel)theta; >> } >> - edgePic[middle] = (pixel)(gradientMagnitude >= >> edgeThreshold ? edgeThreshold : blackPixel); >> + edgePic[middle] = (pixel)(gradientMagnitude >= >> EDGE_THRESHOLD ? whitePixel : blackPixel); >> } >> } >> return true; >> @@ -519,6 +519,14 @@ >> if (param->rc.aqMode == X265_AQ_EDGE) >> edgeFilter(curFrame, param); >> >> + if (param->rc.aqMode == X265_AQ_EDGE && >> !param->bHistBasedSceneCut && param->bEnableRecursionSkip == >> EDGE_BASED_RSKIP) >> + { >> + pixel* src = curFrame->m_edgePic + >> curFrame->m_fencPic->m_lumaMarginY * curFrame->m_fencPic->m_stride + >> curFrame->m_fencPic->m_lumaMarginX; >> + pixel* dst = curFrame->m_edgeBitPlane + >> curFrame->m_fencPic->m_lumaMarginY * curFrame->m_fencPic->m_stride + >> curFrame->m_fencPic->m_lumaMarginX; >> + primitives.planecopy_pp_shr(src, >> curFrame->m_fencPic->m_stride, dst, >> + curFrame->m_fencPic->m_stride, >> curFrame->m_fencPic->m_picWidth, curFrame->m_fencPic->m_picHeight, >> SHIFT_TO_BITPLANE); >> + } >> + >> if (param->rc.aqMode == X265_AQ_AUTO_VARIANCE || >> param->rc.aqMode == X265_AQ_AUTO_VARIANCE_BIASED || param->rc.aqMode == >> X265_AQ_EDGE) >> { >> double bit_depth_correction = 1.f / (1 << (2 * >> (X265_DEPTH - 8))); >> diff -r acc5d16999e2 -r e0e0270ead41 source/encoder/slicetype.h >> --- a/source/encoder/slicetype.h Mon Jan 20 18:07:59 2020 +0530 >> +++ b/source/encoder/slicetype.h Tue Jan 21 10:53:49 2020 +0530 >> @@ -44,9 +44,9 @@ >> #define EDGE_INCLINATION 45 >> >> #if HIGH_BIT_DEPTH >> -#define edgeThreshold 1023.0 >> +#define EDGE_THRESHOLD 1023.0 >> #else >> -#define edgeThreshold 255.0 >> +#define EDGE_THRESHOLD 255.0 >> #endif >> #define PI 3.14159265 >> >> @@ -101,7 +101,7 @@ >> protected: >> >> uint32_t acEnergyCu(Frame* curFrame, uint32_t blockX, uint32_t >> blockY, int csp, uint32_t qgSize); >> - uint32_t edgeDensityCu(Frame*curFrame, uint32_t &avgAngle, uint32_t >> blockX, uint32_t blockY, uint32_t qgSize); >> + uint32_t edgeDensityCu(Frame* curFrame, uint32_t &avgAngle, uint32_t >> blockX, uint32_t blockY, uint32_t qgSize); >> uint32_t lumaSumCu(Frame* curFrame, uint32_t blockX, uint32_t >> blockY, uint32_t qgSize); >> uint32_t weightCostLuma(Lowres& fenc, Lowres& ref, WeightParam& wp); >> bool allocWeightedRef(Lowres& fenc); >> @@ -265,7 +265,6 @@ >> CostEstimateGroup& operator=(const CostEstimateGroup&); >> }; >> >> -bool computeEdge(pixel *edgePic, pixel *refPic, pixel *edgeTheta, >> intptr_t stride, int height, int width, bool bcalcTheta); >> - >> +bool computeEdge(pixel* edgePic, pixel* refPic, pixel* edgeTheta, >> intptr_t stride, int height, int width, bool bcalcTheta, pixel whitePixel = >> EDGE_THRESHOLD); >> } >> #endif // ifndef X265_SLICETYPE_H >> diff -r acc5d16999e2 -r e0e0270ead41 source/test/regression-tests.txt >> --- a/source/test/regression-tests.txt Mon Jan 20 18:07:59 2020 +0530 >> +++ b/source/test/regression-tests.txt Tue Jan 21 10:53:49 2020 +0530 >> @@ -161,6 +161,10 @@ >> Island_960x540_24.yuv,--no-cutree --aq-mode 0 --bitrate 6000 >> --scenecut-aware-qp >> sintel_trailer_2k_1920x1080_24.yuv, --preset medium --hist-scenecut >> --hist-threshold 0.02 --frame-dup --dup-threshold 60 --hrd --bitrate 10000 >> --vbv-bufsize 15000 --vbv-maxrate 12000 >> sintel_trailer_2k_1920x1080_24.yuv, --preset medium --hist-scenecut >> --hist-threshold 0.02 >> +crowd_run_1080p50.yuv, --preset faster --ctu 32 --rskip 2 >> --edge-threshold 5 >> +crowd_run_1080p50.yuv, --preset fast --ctu 64 --rskip 2 --edge-threshold >> 5 --aq-mode 4 >> +crowd_run_1080p50.yuv, --preset slow --ctu 32 --rskip 2 --edge-threshold >> 5 --hist-scenecut --hist-threshold 0.1 >> +crowd_run_1080p50.yuv, --preset veryslow --ctu 16 --rskip 2 >> --edge-threshold 5 --hist-scenecut --hist-threshold 0.1 --aq-mode 4 >> > [KS] I don't understand the purpose to test veryslow with rskip 2 when > this algorithm works only for rd 0 to 4 (atleast this patch does only > that). > Please clarify your intention for adding this command > >> >> # Main12 intraCost overflow bug test >> 720p50_parkrun_ter.y4m,--preset medium >> diff -r acc5d16999e2 -r e0e0270ead41 source/x265.h >> --- a/source/x265.h Mon Jan 20 18:07:59 2020 +0530 >> +++ b/source/x265.h Tue Jan 21 10:53:49 2020 +0530 >> @@ -1857,7 +1857,7 @@ >> double edgeTransitionThreshold; >> >> /* Enables histogram based scenecut detection algorithm to detect >> scenecuts. Default disabled */ >> - int bHistBasedSceneCut; >> + int bHistBasedSceneCut; >> >> /* Enable HME search ranges for L0, L1 and L2 respectively. */ >> int hmeRange[3]; >> @@ -1874,7 +1874,7 @@ >> * analysis information stored in analysis-save. Higher the refine >> level higher >> * the information stored. Default is 5 */ >> int analysisSaveReuseLevel; >> - >> + >> /* A value between 1 and 10 (both inclusive) determines the level of >> * analysis information reused in analysis-load. Higher the refine >> level higher >> * the information reused. Default is 5 */ >> @@ -1901,6 +1901,9 @@ >> * info is available from the corresponding analysis-save. */ >> >> int confWinBottomOffset; >> + >> + /* Edge variance threshold for quad tree establishment. */ >> + float edgeThreshold; >> } x265_param; >> >> /* x265_param_alloc: >> diff -r acc5d16999e2 -r e0e0270ead41 source/x265cli.h >> --- a/source/x265cli.h Mon Jan 20 18:07:59 2020 +0530 >> +++ b/source/x265cli.h Tue Jan 21 10:53:49 2020 +0530 >> @@ -105,8 +105,8 @@ >> { "amp", no_argument, NULL, 0 }, >> { "no-early-skip", no_argument, NULL, 0 }, >> { "early-skip", no_argument, NULL, 0 }, >> - { "no-rskip", no_argument, NULL, 0 }, >> - { "rskip", no_argument, NULL, 0 }, >> + { "rskip", required_argument, NULL, 0 }, >> + { "edge-threshold", required_argument, NULL, 0 }, >> { "no-fast-cbf", no_argument, NULL, 0 }, >> { "fast-cbf", no_argument, NULL, 0 }, >> { "no-tskip", no_argument, NULL, 0 }, >> @@ -457,7 +457,8 @@ >> H0(" --[no-]ssim-rd Enable ssim rate distortion >> optimization, 0 to disable. Default %s\n", OPT(param->bSsimRd)); >> H0(" --[no-]rd-refine Enable QP based RD refinement >> for rd levels 5 and 6. Default %s\n", OPT(param->bEnableRdRefine)); >> H0(" --[no-]early-skip Enable early SKIP detection. >> Default %s\n", OPT(param->bEnableEarlySkip)); >> - H0(" --[no-]rskip Enable early exit from >> recursion. Default %s\n", OPT(param->bEnableRecursionSkip)); >> + H0(" --rskip <mode> Set mode for early exit from >> recursion. Mode 1: exit using rdcost. Mode 2: exit using edge density. Mode >> 0: disabled. Default %s\n", OPT(param->bEnableRecursionSkip)); >> + H1(" --edge-threshold Threshold in terms of >> percentage for minimum edge density in CUs to terminate the recursion >> depth. Applicable only for rskip mode 2. Default %s\n", >> OPT(param->edgeThreshold)); >> H1(" --[no-]tskip-fast Enable fast intra transform >> skipping. Default %s\n", OPT(param->bEnableTSkipFast)); >> H1(" --[no-]splitrd-skip Enable skipping split RD >> analysis when sum of split CU rdCost larger than one split CU rdCost for >> Intra CU. Default %s\n", OPT(param->bEnableSplitRdSkip)); >> H1(" --nr-intra <integer> An integer value in range of 0 >> to 2000, which denotes strength of noise reduction in intra CUs. Default >> 0\n"); >> _______________________________________________ >> x265-devel mailing list >> x265-devel@videolan.org >> https://mailman.videolan.org/listinfo/x265-devel >> > > > -- > Regards, > Kavitha > _______________________________________________ > x265-devel mailing list > x265-devel@videolan.org > https://mailman.videolan.org/listinfo/x265-devel >
_______________________________________________ x265-devel mailing list x265-devel@videolan.org https://mailman.videolan.org/listinfo/x265-devel