HM代码阅读5：快速大范围运动估计函数xTZSearch()与xTZ8PointDiaMondSearch()

上一次讲过了全搜索的做法，主要用于第二次对cost较大的参考图像列表的对应MV做一定范围内的全搜索减小cost。

这次主要讲在第一次做ME时的快速搜索算法，HM中采用TZSearch进行大范围内的ME。HM中提供的算法如下：
一般是采用Diamond搜索，也就是菱形搜索，在进搜索函数之前需要找到左、上、右上的MV，来判断是不是邻居MV更适合做ME的起始点（这里书本中没有详细写明，要注意）

Void TEncSearch::xPatternSearchFast( const TComDataCU* const  pcCU,
                                     const TComPattern* const pcPatternKey,
                                     const Pel* const         piRefY,
                                     const Int                iRefStride,
                                     const TComMv* const      pcMvSrchRngLT,
                                     const TComMv* const      pcMvSrchRngRB,
                                     TComMv&                  rcMv,
                                     Distortion&              ruiSAD,
                                     const TComMv* const      pIntegerMv2Nx2NPred )
{
   
  assert (MD_LEFT < NUM_MV_PREDICTORS);
  pcCU->getMvPredLeft       ( m_acMvPredictors[MD_LEFT] );
  assert (MD_ABOVE < NUM_MV_PREDICTORS);
  pcCU->getMvPredAbove      ( m_acMvPredictors[MD_ABOVE] );
  assert (MD_ABOVE_RIGHT < NUM_MV_PREDICTORS);
  pcCU->getMvPredAboveRight ( m_acMvPredictors[MD_ABOVE_RIGHT] );

  switch ( m_motionEstimationSearchMethod )
  {
   
    case MESEARCH_DIAMOND:
      xTZSearch( pcCU, pcPatternKey, piRefY, iRefStride, pcMvSrchRngLT, pcMvSrchRngRB, rcMv, ruiSAD, pIntegerMv2Nx2NPred, false );
      break;

    case MESEARCH_SELECTIVE:
      xTZSearchSelective( pcCU, pcPatternKey, piRefY, iRefStride, pcMvSrchRngLT, pcMvSrchRngRB, rcMv, ruiSAD, pIntegerMv2Nx2NPred );
      break;

    case MESEARCH_DIAMOND_ENHANCED:
      xTZSearch( pcCU, pcPatternKey, piRefY, iRefStride, pcMvSrchRngLT, pcMvSrchRngRB, rcMv, ruiSAD, pIntegerMv2Nx2NPred, true );
      break;

    case MESEARCH_FULL: // shouldn't get here.
    default:
      break;
  }
}

接下来是菱形搜索的具体过程
1、预先设置搜索的参数，如：逐行搜索还是菱形搜索，精调时选star菱形搜索还是逐行搜索，是否考虑角落等。

2、定义结构体IntTZSearchStruct ，用于存储当前最好的MV以及最小失真，以及重建帧的同位起始地址、步幅等。

3、调用xTZSearchHelp去判断最好的起始位置，需要依次考虑 当前最佳MVP、左、上、右上MVP、0运动矢量、若不是2NX2N的块，还需要判断一下2NX2N的块是不是最佳起始位置。

4、开始做菱形搜索，菱形搜索如图所示：

• 步长从1 到 64 每次增加2倍。能够得到当前最佳运动矢量。 再以0矢量为起始点，再进行同样的搜索，对比两次结果找到最优MV。
• 如果是在distance=1时找到最优的MV，那还需进行一次两点搜索。
• 以当前最佳MV进行starRefine，以同样的方式进行8点菱形搜索。
  代码如下：

Void TEncSearch::xTZSearch( const TComDataCU* const pcCU,
                            const TComPattern* const pcPatternKey,
                            const Pel* const         piRefY,
                            const Int                iRefStride,
                            const TComMv* const      pcMvSrchRngLT,
                            const TComMv* const      pcMvSrchRngRB,
                            TComMv&                  rcMv,
                            Distortion&              ruiSAD,
                            const TComMv* const      pIntegerMv2Nx2NPred,
                            const Bool               bExtendedSettings)
{
   
  const Bool bUseAdaptiveRaster                      = bExtendedSettings;
  const Int  iRaster                                 = 5;
  const Bool bTestOtherPredictedMV                   = bExtendedSettings;
  const Bool bTestZeroVector                         = true;
  const Bool bTestZeroVectorStart                    = bExtendedSettings;
  const Bool bTestZeroVectorStop                     = false;
  const Bool bFirstSearchDiamond                     = true;  // 1 = xTZ8PointDiamondSearch   0 = xTZ8PointSquareSearch
  const Bool bFirstCornersForDiamondDist1            = bExtendedSettings;
  const Bool bFirstSearchStop                        = m_pcEncCfg->getFastMEAssumingSmootherMVEnabled();
  const UInt uiFirstSearchRounds                     = 3;     // first search stop X rounds after best match (must be >=1)
  const Bool bEnableRasterSearch                     = true;
  const Bool bAlwaysRasterSearch                     = bExtendedSettings;  // true: BETTER but factor 2 slower
  const Bool bRasterRefinementEnable                 = false; // enable either raster refinement or star refinement
  const Bool bRasterRefinementDiamond                = false; // 1 = xTZ8PointDiamondSearch   0 = xTZ8PointSquareSearch
  const Bool bRasterRefinementCornersForDiamondDist1 = bExtendedSettings;
  const Bool bStarRefinementEnable                   = true;  // enable either star refinement or raster refinement
  const Bool bStarRefinementDiamond                  = true;  // 1 = xTZ8PointDiamondSearch   0 = xTZ8PointSquareSearch
  const Bool bStarRefinementCornersForDiamondDist1   = bExtendedSettings;
  const Bool bStarRefinementStop                     = false;
  const UInt uiStarRefinementRounds                  = 2;  // star refinement stop X rounds after best match (must be >=1)
  const Bool bNewZeroNeighbourhoodTest               = bExtendedSettings;

  UInt uiSearchRange = m_iSearchRange;
  pcCU->clipMv( rcMv );
#if ME_ENABLE_ROUNDING_OF_MVS
  rcMv.divideByPowerOf2(2);
#else
  rcMv >>= 2;
#endif
  // init TZSearchStruct
  IntTZSearchStruct cStruct;
  cStruct.iYStride    = iRefStride;
  cStruct.piRefY      = piRefY;
  cStruct.uiBestSad   = MAX_UINT;

  // set rcMv (Median predictor) as start point and as best point
  xTZSearchHelp( pcPatternKey, cStruct, rcMv.getHor(), rcMv.getVer(), 0, 0 );

  // test whether one of PRED_A, PRED_B, PRED_C MV is better start point than Median predictor
  if ( bTestOtherPredictedMV )
  {
   
    for ( UInt index = 0; index < NUM_MV_PREDICTORS; index++ )
    {
   
      TComMv cMv = m_acMvPredictors[index];
      pcCU->clipMv( cMv );
#if ME_ENABLE_ROUNDING_OF_MVS
      cMv.divideByPowerOf2(2);
#else
      cMv >>= 2;
#endif
      if (cMv != rcMv && (cMv.getHor() != cStruct.iBestX && cMv.getVer() != cStruct.iBestY))
      {
   
        // only test cMV if not obviously previously tested.
        xTZSearchHelp( pcPatternKey, cStruct, cMv.getHor(), cMv.getVer(), 0, 0