[x265] [PATCH] Enabling weight prediction for half and full pel
shazeb at multicorewareinc.com
shazeb at multicorewareinc.com
Wed Oct 9 09:54:13 CEST 2013
# HG changeset patch
# User Shazeb Nawaz Khan <shazeb at multicorewareinc.com>
# Date 1381305224 -19800
# Wed Oct 09 13:23:44 2013 +0530
# Node ID 233ac9a05362715f2523f51e39a5961af46813de
# Parent fc7fbdd18bc0d6d7f98180332e065d83c054fe02
Enabling weight prediction for half and full pel
diff -r fc7fbdd18bc0 -r 233ac9a05362 source/common/reference.cpp
--- a/source/common/reference.cpp Wed Oct 09 00:00:10 2013 -0500
+++ b/source/common/reference.cpp Wed Oct 09 13:23:44 2013 +0530
@@ -58,6 +58,7 @@
int MotionReference::init(TComPicYuv* pic, wpScalingParam *w)
{
m_reconPic = pic;
+ unweightedFPelPlane = pic->getLumaAddr();
lumaStride = pic->getStride();
m_startPad = pic->m_lumaMarginY * lumaStride + pic->m_lumaMarginX;
m_next = NULL;
@@ -89,21 +90,19 @@
X265_FREE(fpelPlane - m_startPad);
}
-void MotionReference::applyWeight(TComPic* ref, int rows, int numRows)
+void MotionReference::applyWeight(int rows, int numRows)
{
rows = X265_MIN(rows, numRows-1);
if (m_numWeightedRows >= rows)
return;
-
- TComPicYuv* pic = ref->getPicYuvRec();
- int marginX = pic->m_lumaMarginX;
- int marginY = pic->m_lumaMarginY;
- pixel* src = (pixel*) pic->getLumaAddr() + (m_numWeightedRows * (int)g_maxCUHeight * lumaStride);
+ int marginX = m_reconPic->m_lumaMarginX;
+ int marginY = m_reconPic->m_lumaMarginY;
+ pixel* src = (pixel*) m_reconPic->getLumaAddr() + (m_numWeightedRows * (int)g_maxCUHeight * lumaStride);
pixel* dst = fpelPlane + ((m_numWeightedRows * (int)g_maxCUHeight) * lumaStride);
- int width = pic->getWidth();
+ int width = m_reconPic->getWidth();
int height = ((rows - m_numWeightedRows) * g_maxCUHeight);
if (rows == numRows - 1)
- height = ((pic->getHeight() % g_maxCUHeight) ? (pic->getHeight() % g_maxCUHeight) : g_maxCUHeight);
+ height = ((m_reconPic->getHeight() % g_maxCUHeight) ? (m_reconPic->getHeight() % g_maxCUHeight) : g_maxCUHeight);
size_t dstStride = lumaStride;
// Computing weighted CU rows
@@ -128,7 +127,7 @@
// Extending Bottom
if (rows == (numRows - 1))
{
- pixel *pixY = fpelPlane - marginX + (pic->getHeight() - 1) * dstStride;
+ pixel *pixY = fpelPlane - marginX + (m_reconPic->getHeight() - 1) * dstStride;
for (int y = 0; y < marginY; y++)
{
memcpy(pixY + (y + 1) * dstStride, pixY, dstStride * sizeof(pixel));
diff -r fc7fbdd18bc0 -r 233ac9a05362 source/common/reference.h
--- a/source/common/reference.h Wed Oct 09 00:00:10 2013 -0500
+++ b/source/common/reference.h Wed Oct 09 13:23:44 2013 +0530
@@ -43,6 +43,7 @@
pixel* fpelPlane;
pixel* lowresPlane[4];
+ pixel* unweightedFPelPlane;
bool isWeighted;
bool isLowres;
@@ -60,7 +61,7 @@
MotionReference();
~MotionReference();
int init(TComPicYuv*, wpScalingParam* w = NULL);
- void applyWeight(TComPic* src, int rows, int numRows);
+ void applyWeight(int rows, int numRows);
MotionReference *m_next;
TComPicYuv *m_reconPic;
diff -r fc7fbdd18bc0 -r 233ac9a05362 source/encoder/frameencoder.cpp
--- a/source/encoder/frameencoder.cpp Wed Oct 09 00:00:10 2013 -0500
+++ b/source/encoder/frameencoder.cpp Wed Oct 09 13:23:44 2013 +0530
@@ -972,6 +972,10 @@
{
refpic->m_reconRowWait.wait();
}
+ if (slice->getPPS()->getUseWP() && (slice->getSliceType() == P_SLICE))
+ {
+ slice->m_mref[list][ref]->applyWeight(row + refLagRows, m_numRows);
+ }
}
}
@@ -1004,6 +1008,10 @@
{
refpic->m_reconRowWait.wait();
}
+ if (slice->getPPS()->getUseWP() && (slice->getSliceType() == P_SLICE))
+ {
+ slice->m_mref[list][ref]->applyWeight(i + refLagRows, m_numRows);
+ }
}
}
diff -r fc7fbdd18bc0 -r 233ac9a05362 source/encoder/motion.cpp
--- a/source/encoder/motion.cpp Wed Oct 09 00:00:10 2013 -0500
+++ b/source/encoder/motion.cpp Wed Oct 09 13:23:44 2013 +0530
@@ -89,6 +89,7 @@
fenc = (pixel*)X265_MALLOC(pixel, MAX_CU_SIZE * MAX_CU_SIZE);
subpelbuf = (pixel*)X265_MALLOC(pixel, (MAX_CU_SIZE + 1) * (MAX_CU_SIZE + 1));
immedVal = (short*)X265_MALLOC(short, (MAX_CU_SIZE + 1) * (MAX_CU_SIZE + 1 + NTAPS_LUMA - 1));
+ immedVal2 = (int16_t*)X265_MALLOC(int16_t, (MAX_CU_SIZE + 1) * (MAX_CU_SIZE + 1 + NTAPS_LUMA - 1));
}
MotionEstimate::~MotionEstimate()
@@ -96,6 +97,7 @@
X265_FREE(fenc);
X265_FREE(subpelbuf);
X265_FREE(immedVal);
+ X265_FREE(immedVal2);
}
void MotionEstimate::setSourcePU(int offset, int width, int height)
@@ -831,7 +833,7 @@
}
else
{
- subpelInterpolate(fqref, ref->lumaStride, xFrac, yFrac, dir);
+ subpelInterpolate(ref, qmv0, dir);
cost0 = hpelcomp(fenc, FENC_STRIDE, subpelbuf, FENC_STRIDE + (dir == 2)) + mvcost0;
cost1 = hpelcomp(fenc, FENC_STRIDE, subpelbuf + (dir == 2) + (dir == 1 ? FENC_STRIDE : 0), FENC_STRIDE + (dir == 2)) + mvcost1;
}
@@ -1140,47 +1142,61 @@
{
return cmp(fenc, FENC_STRIDE, fref, ref->lumaStride);
}
- else if (yFrac == 0)
+ else
{
- primitives.ipfilter_pp[FILTER_H_P_P_8](fref, ref->lumaStride, subpelbuf, FENC_STRIDE, blockwidth, blockheight, g_lumaFilter[xFrac]);
+ subpelInterpolate(ref, qmv, 0);
+ }
+ return cmp(fenc, FENC_STRIDE, subpelbuf, FENC_STRIDE);
+ }
+}
+
+void MotionEstimate::subpelInterpolate(ReferencePlanes *ref, MV qmv, int dir)
+{
+ int xFrac = qmv.x & 0x3;
+ int yFrac = qmv.y & 0x3;
+ assert(yFrac | xFrac);
+ int realWidth = blockwidth + (dir == 2);
+ int realHeight = blockheight + (dir == 1);
+ intptr_t realStride = FENC_STRIDE + (dir == 2);
+ pixel *fref = ref->unweightedFPelPlane + blockOffset + (qmv.x >> 2) + (qmv.y >> 2) * ref->lumaStride;
+
+ if (ref->isWeighted)
+ {
+ if (yFrac == 0)
+ {
+ primitives.ipfilter_ps[FILTER_H_P_S_8](fref, ref->lumaStride, immedVal, realStride, realWidth, realHeight, g_lumaFilter[xFrac]);
+ primitives.weightpUni(immedVal, subpelbuf, realStride, realStride, realWidth, realHeight, ref->weight, ref->round, ref->shift, ref->offset);
}
else if (xFrac == 0)
{
- primitives.ipfilter_pp[FILTER_V_P_P_8](fref, ref->lumaStride, subpelbuf, FENC_STRIDE, blockwidth, blockheight, g_lumaFilter[yFrac]);
+ primitives.ipfilter_ps[FILTER_V_P_S_8](fref, ref->lumaStride, immedVal, realStride, realWidth, realHeight, g_lumaFilter[yFrac]);
+ primitives.weightpUni(immedVal, subpelbuf, realStride, realStride, realWidth, realHeight, ref->weight, ref->round, ref->shift, ref->offset);
}
else
{
int filterSize = NTAPS_LUMA;
int halfFilterSize = (filterSize >> 1);
- primitives.ipfilter_ps[FILTER_H_P_S_8](fref - (halfFilterSize - 1) * ref->lumaStride, ref->lumaStride, immedVal, blockwidth, blockwidth, blockheight + filterSize - 1, g_lumaFilter[xFrac]);
- primitives.ipfilter_sp[FILTER_V_S_P_8](immedVal + (halfFilterSize - 1) * blockwidth, blockwidth, subpelbuf, FENC_STRIDE, blockwidth, blockheight, g_lumaFilter[yFrac]);
+ primitives.ipfilter_ps[FILTER_H_P_S_8](fref - (halfFilterSize - 1) * ref->lumaStride, ref->lumaStride, immedVal, realWidth, realWidth, realHeight + filterSize - 1, g_lumaFilter[xFrac]);
+ primitives.ipfilter_ss[FILTER_V_S_S_8](immedVal + (halfFilterSize - 1) * realWidth, realWidth, immedVal2, realStride, realWidth, realHeight, g_lumaFilter[yFrac]);
+ primitives.weightpUni(immedVal2, subpelbuf, realStride, realStride, realWidth, realHeight, ref->weight, ref->round, ref->shift, ref->offset);
}
-
- return cmp(fenc, FENC_STRIDE, subpelbuf, FENC_STRIDE);
- }
-}
-
-void MotionEstimate::subpelInterpolate(pixel *fref, intptr_t lumaStride, int xFrac, int yFrac, int dir)
-{
- assert(yFrac | xFrac);
-
- int realWidth = blockwidth + (dir == 2);
- int realHeight = blockheight + (dir == 1);
- intptr_t realStride = FENC_STRIDE + (dir == 2);
-
- if (yFrac == 0)
- {
- primitives.ipfilter_pp[FILTER_H_P_P_8](fref, lumaStride, subpelbuf, realStride, realWidth, realHeight, g_lumaFilter[xFrac]);
- }
- else if (xFrac == 0)
- {
- primitives.ipfilter_pp[FILTER_V_P_P_8](fref, lumaStride, subpelbuf, realStride, realWidth, realHeight, g_lumaFilter[yFrac]);
}
else
{
- int filterSize = NTAPS_LUMA;
- int halfFilterSize = (filterSize >> 1);
- primitives.ipfilter_ps[FILTER_H_P_S_8](fref - (halfFilterSize - 1) * lumaStride, lumaStride, immedVal, realWidth, realWidth, realHeight + filterSize - 1, g_lumaFilter[xFrac]);
- primitives.ipfilter_sp[FILTER_V_S_P_8](immedVal + (halfFilterSize - 1) * realWidth, realWidth, subpelbuf, realStride, realWidth, realHeight, g_lumaFilter[yFrac]);
+ if (yFrac == 0)
+ {
+ primitives.ipfilter_pp[FILTER_H_P_P_8](fref, ref->lumaStride, subpelbuf, realStride, realWidth, realHeight, g_lumaFilter[xFrac]);
+ }
+ else if (xFrac == 0)
+ {
+ primitives.ipfilter_pp[FILTER_V_P_P_8](fref, ref->lumaStride, subpelbuf, realStride, realWidth, realHeight, g_lumaFilter[yFrac]);
+ }
+ else
+ {
+ int filterSize = NTAPS_LUMA;
+ int halfFilterSize = (filterSize >> 1);
+ primitives.ipfilter_ps[FILTER_H_P_S_8](fref - (halfFilterSize - 1) * ref->lumaStride, ref->lumaStride, immedVal, realWidth, realWidth, realHeight + filterSize - 1, g_lumaFilter[xFrac]);
+ primitives.ipfilter_sp[FILTER_V_S_P_8](immedVal + (halfFilterSize - 1) * realWidth, realWidth, subpelbuf, realStride, realWidth, realHeight, g_lumaFilter[yFrac]);
+ }
}
}
diff -r fc7fbdd18bc0 -r 233ac9a05362 source/encoder/motion.h
--- a/source/encoder/motion.h Wed Oct 09 00:00:10 2013 -0500
+++ b/source/encoder/motion.h Wed Oct 09 13:23:44 2013 +0530
@@ -54,6 +54,7 @@
/* subpel generation buffers */
pixel *subpelbuf;
short *immedVal;
+ int16_t *immedVal2;
int blockwidth;
int blockheight;
@@ -96,7 +97,7 @@
int subpelCompare(ReferencePlanes *ref, const MV & qmv, pixelcmp_t);
- void subpelInterpolate(pixel *fref, intptr_t lumaStride, int xFrac, int yFrac, int dir);
+ inline void subpelInterpolate(ReferencePlanes *ref, MV qmv, int dir);
protected:
More information about the x265-devel
mailing list