[x265] [PATCH] no-rdo: giving weightage to the cost of all CU's and neighbour CU's for early exit

[sumalatha at multicorewareinc.com]

# HG changeset patch
# User Sumalatha Polureddy
# Date 1383823751 -19800
# Node ID a54b30b16e83048a7a2ef5584e1e1c9682216075
# Parent  0a1b379be359cbcf76140ac392104c856a037c78
no-rdo: giving weightage to the cost of all CU's and neighbour CU's for early exit

Early exit is done when CU cost at depth "n" is lessthan sum of 60% of avgcost of all CU's
and 40% of avgcost of neighbour CU's at same depth.

diff -r 0a1b379be359 -r a54b30b16e83 source/Lib/TLibCommon/TComPic.cpp
--- a/source/Lib/TLibCommon/TComPic.cpp	Thu Nov 07 18:17:52 2013 +0800
+++ b/source/Lib/TLibCommon/TComPic.cpp	Thu Nov 07 16:59:11 2013 +0530
@@ -69,6 +69,14 @@
     m_ssimCnt = 0;
     m_frameTime = 0.0;
     m_elapsedCompressTime = 0.0;
+    m_avgCost[0] = 0;
+    m_avgCost[1] = 0;
+    m_avgCost[2] = 0;
+    m_avgCost[3] = 0;
+    m_count[0] = 0;
+    m_count[1] = 0;
+    m_count[2] = 0;
+    m_count[3] = 0;
 }
 
 TComPic::~TComPic()
diff -r 0a1b379be359 -r a54b30b16e83 source/Lib/TLibCommon/TComPic.h
--- a/source/Lib/TLibCommon/TComPic.h	Thu Nov 07 18:17:52 2013 +0800
+++ b/source/Lib/TLibCommon/TComPic.h	Thu Nov 07 16:59:11 2013 +0530
@@ -95,6 +95,8 @@
     MD5Context            m_state[3];
     uint32_t              m_crc[3];
     uint32_t              m_checksum[3];
+    UInt64                m_avgCost[4];
+    uint32_t              m_count[4];
 
     /* SSIM values per frame */
     double                m_ssim;
diff -r 0a1b379be359 -r a54b30b16e83 source/encoder/compress.cpp
--- a/source/encoder/compress.cpp	Thu Nov 07 18:17:52 2013 +0800
+++ b/source/encoder/compress.cpp	Thu Nov 07 16:59:11 2013 +0530
@@ -567,13 +567,14 @@
     if (bSubBranch && bTrySplitDQP && depth < g_maxCUDepth - g_addCUDepth)
     {
 #if EARLY_EXIT // turn ON this to enable early exit
-        // early exit when the RD cost of best mode at depth n is less than the avgerage of RD cost of the
-        // CU's(above, aboveleft, aboveright, left, colocated) at depth "n" of previosuly coded CU's
+        // early exit when the RD cost of best mode at depth n is less than the sum of avgerage of RD cost of the neighbour 
+        // CU's(above, aboveleft, aboveright, left, colocated) and all CU's at depth "n"  with weightage for each quantity
         if (outBestCU != 0)
         {
-            UInt64 costCU = 0, costCUAbove = 0, costCUAboveLeft = 0, costCUAboveRight = 0, costCULeft = 0, costCUColocated0 = 0, costCUColocated1 = 0, totalCost = 0, avgCost = 0;
+            UInt64 costCU = 0, costCUAbove = 0, costCUAboveLeft = 0, costCUAboveRight = 0, costCULeft = 0, costCUColocated0 = 0, costCUColocated1 = 0, totalCostNeigh = 0, totalCostAll = 0;
+            double avgCost = 0;
             UInt64 countCU = 0, countCUAbove = 0, countCUAboveLeft = 0, countCUAboveRight = 0, countCULeft = 0, countCUColocated0 = 0, countCUColocated1 = 0;
-            UInt64 totalCount = 0;
+            UInt64 totalCountNeigh = 0, totalCountAll = 0;
             TComDataCU* above = outTempCU->getCUAbove();
             TComDataCU* aboveLeft = outTempCU->getCUAboveLeft();
             TComDataCU* aboveRight = outTempCU->getCUAboveRight();
@@ -614,10 +615,15 @@
                 countCUColocated1 = colocated1->m_count[depth];
             }
 
-            totalCost = costCU + costCUAbove + costCUAboveLeft + costCUAboveRight + costCULeft + costCUColocated0 + costCUColocated1;
-            totalCount = countCU + countCUAbove + countCUAboveLeft + countCUAboveRight + countCULeft + countCUColocated0 + countCUColocated1;
-            if (totalCount != 0)
-                avgCost = totalCost / totalCount;
+            totalCostNeigh = costCU + costCUAbove + costCUAboveLeft + costCUAboveRight + costCULeft + costCUColocated0 + costCUColocated1;
+            totalCountNeigh = countCU + countCUAbove + countCUAboveLeft + countCUAboveRight + countCULeft + countCUColocated0 + countCUColocated1;
+
+            totalCostAll = (outTempCU->getPic()->m_avgCost[depth] * outTempCU->getPic()->m_count[depth]) - totalCostNeigh;
+            totalCountAll = outTempCU->getPic()->m_count[depth] - totalCountNeigh;
+
+            //giving 60% weight to all CU's and 40% weight to neighbour CU's
+            if (totalCountAll)
+                avgCost = ((0.6 * totalCostAll) + (0.4 * totalCostNeigh)) / ((0.6 * totalCountAll) + (0.4 * totalCountNeigh));
 
             float lambda = 1.0f;
 
@@ -672,6 +678,9 @@
                     outTempCU->getPic()->getPicSym()->getCU(outTempCU->getAddr())->m_count[depth + 1] += 1;
                     outTempCU->m_avgCost[depth + 1] = (temp + tempavgCost) / outTempCU->m_count[depth + 1];
                     outTempCU->getPic()->getPicSym()->getCU(outTempCU->getAddr())->m_avgCost[depth + 1] = outTempCU->m_avgCost[depth + 1];
+                    temp = outTempCU->getPic()->m_avgCost[depth+1] * outTempCU->getPic()->m_count[depth+1];
+                    outTempCU->getPic()->m_count[depth+1] += 1;
+                    outTempCU->getPic()->m_avgCost[depth+1] = (temp + tempavgCost) / outTempCU->getPic()->m_count[depth+1];
                 }
 #endif // if EARLY_EXIT
                 /* Adding costs from best SUbCUs */
@@ -775,9 +784,12 @@
                 UInt64 temp = outTempCU->m_avgCost[depth] * outTempCU->m_count[depth];
                 outTempCU->m_count[depth] += 1;
                 outTempCU->getPic()->getPicSym()->getCU(outTempCU->getAddr())->m_count[depth] += 1;
-
                 outTempCU->m_avgCost[depth] = (temp + tempavgCost) / outTempCU->m_count[depth];
                 outTempCU->getPic()->getPicSym()->getCU(outTempCU->getAddr())->m_avgCost[depth] = outTempCU->m_avgCost[depth];
+
+                temp = outTempCU->getPic()->m_avgCost[depth] * outTempCU->getPic()->m_count[depth];
+                outTempCU->getPic()->m_count[depth] += 1;
+                outTempCU->getPic()->m_avgCost[depth] = (temp + tempavgCost) / outTempCU->getPic()->m_count[depth];
             }
             if (outTempCU->m_totalCost < outBestCU->m_totalCost)
             {