mv-search.c

avs-s最新代码,包括编码器和解码器源码

    cand_y = center_y + spiral_search_y[pos];

    //--- initialize motion cost (cost for motion vector) and check ---
    mcost = MV_COST (lambda_factor, 2, cand_x, cand_y, pred_x, pred_y);
    if (check_for_00 && cand_x==pic_pix_x && cand_y==pic_pix_y)
    {
      mcost -= WEIGHTED_COST (lambda_factor, 16);
    }
    
    if (mcost >= min_mcost)
      continue;

    //--- add residual cost to motion cost ---
    for (y=0; y<blocksize_y; y++)
    {
      ref_line  = get_ref_line (blocksize_x, ref_pic, cand_y+y, cand_x);
      orig_line = orig_pic [y];

      for (x8=0; x8<blocksize_x8; x8++)
      {
        mcost += byte_abs[ *orig_line++ - *ref_line++ ];
        mcost += byte_abs[ *orig_line++ - *ref_line++ ];
        mcost += byte_abs[ *orig_line++ - *ref_line++ ];
        mcost += byte_abs[ *orig_line++ - *ref_line++ ];
        mcost += byte_abs[ *orig_line++ - *ref_line++ ];
        mcost += byte_abs[ *orig_line++ - *ref_line++ ];
        mcost += byte_abs[ *orig_line++ - *ref_line++ ];
        mcost += byte_abs[ *orig_line++ - *ref_line++ ];
      }

      if (mcost >= min_mcost)
      {
        break;
      }
    }

    //--- check if motion cost is less than minimum cost ---
    if (mcost < min_mcost)
    {
      best_pos  = pos;
      min_mcost = mcost;
    }
  }

  //===== set best motion vector and return minimum motion cost =====
  if (best_pos)
  {
    *mv_x += spiral_search_x[best_pos];
    *mv_y += spiral_search_y[best_pos];
  }

  return min_mcost;
}

/*
*************************************************************************
* Function:Calculate SA(T)D
* Input:
* Output:
* Return: 
* Attention:
*************************************************************************
*/
int SATD (int* diff, int use_hadamard)
{
  int k, satd = 0, m[16], dd, *d=diff;
  
  if (use_hadamard)
  {
    /*===== hadamard transform =====*/
    m[ 0] = d[ 0] + d[12];
    m[ 4] = d[ 4] + d[ 8];
    m[ 8] = d[ 4] - d[ 8];
    m[12] = d[ 0] - d[12];
    m[ 1] = d[ 1] + d[13];
    m[ 5] = d[ 5] + d[ 9];
    m[ 9] = d[ 5] - d[ 9];
    m[13] = d[ 1] - d[13];
    m[ 2] = d[ 2] + d[14];
    m[ 6] = d[ 6] + d[10];
    m[10] = d[ 6] - d[10];
    m[14] = d[ 2] - d[14];
    m[ 3] = d[ 3] + d[15];
    m[ 7] = d[ 7] + d[11];
    m[11] = d[ 7] - d[11];
    m[15] = d[ 3] - d[15];
    
    d[ 0] = m[ 0] + m[ 4];
    d[ 8] = m[ 0] - m[ 4];
    d[ 4] = m[ 8] + m[12];
    d[12] = m[12] - m[ 8];
    d[ 1] = m[ 1] + m[ 5];
    d[ 9] = m[ 1] - m[ 5];
    d[ 5] = m[ 9] + m[13];
    d[13] = m[13] - m[ 9];
    d[ 2] = m[ 2] + m[ 6];
    d[10] = m[ 2] - m[ 6];
    d[ 6] = m[10] + m[14];
    d[14] = m[14] - m[10];
    d[ 3] = m[ 3] + m[ 7];
    d[11] = m[ 3] - m[ 7];
    d[ 7] = m[11] + m[15];
    d[15] = m[15] - m[11];
    
    m[ 0] = d[ 0] + d[ 3];
    m[ 1] = d[ 1] + d[ 2];
    m[ 2] = d[ 1] - d[ 2];
    m[ 3] = d[ 0] - d[ 3];
    m[ 4] = d[ 4] + d[ 7];
    m[ 5] = d[ 5] + d[ 6];
    m[ 6] = d[ 5] - d[ 6];
    m[ 7] = d[ 4] - d[ 7];
    m[ 8] = d[ 8] + d[11];
    m[ 9] = d[ 9] + d[10];
    m[10] = d[ 9] - d[10];
    m[11] = d[ 8] - d[11];
    m[12] = d[12] + d[15];
    m[13] = d[13] + d[14];
    m[14] = d[13] - d[14];
    m[15] = d[12] - d[15];
    
    d[ 0] = m[ 0] + m[ 1];
    d[ 1] = m[ 0] - m[ 1];
    d[ 2] = m[ 2] + m[ 3];
    d[ 3] = m[ 3] - m[ 2];
    d[ 4] = m[ 4] + m[ 5];
    d[ 5] = m[ 4] - m[ 5];
    d[ 6] = m[ 6] + m[ 7];
    d[ 7] = m[ 7] - m[ 6];
    d[ 8] = m[ 8] + m[ 9];
    d[ 9] = m[ 8] - m[ 9];
    d[10] = m[10] + m[11];
    d[11] = m[11] - m[10];
    d[12] = m[12] + m[13];
    d[13] = m[12] - m[13];
    d[14] = m[14] + m[15];
    d[15] = m[15] - m[14];
    
    /*===== sum up =====*/
    for (dd=diff[k=0]; k<16; dd=diff[++k])
    {
      satd += (dd < 0 ? -dd : dd);
    }
    satd >>= 1;
  }
  else
  {
    /*===== sum up =====*/
    for (k = 0; k < 16; k++)
    {
      satd += byte_abs [diff [k]];
    }
  }
  
  return satd;
}

/*
*************************************************************************
* Function:Sub pixel block motion search
* Input:
* Output:
* Return: 
* Attention:
*************************************************************************
*/

int                                               //  ==> minimum motion cost after search
SubPelBlockMotionSearch (pel_t**   orig_pic,      // <--  original pixel values for the AxB block
                         int       ref,           // <--  reference frame (0... or -1 (backward))
                         int       pic_pix_x,     // <--  absolute x-coordinate of regarded AxB block
                         int       pic_pix_y,     // <--  absolute y-coordinate of regarded AxB block
                         int       blocktype,     // <--  block type (1-16x16 ... 7-4x4)
                         int       pred_mv_x,     // <--  motion vector predictor (x) in sub-pel units
                         int       pred_mv_y,     // <--  motion vector predictor (y) in sub-pel units
                         int*      mv_x,          // <--> in: search center (x) / out: motion vector (x) - in pel units
                         int*      mv_y,          // <--> in: search center (y) / out: motion vector (y) - in pel units
                         int       search_pos2,   // <--  search positions for    half-pel search  (default: 9)
                         int       search_pos4,   // <--  search positions for quarter-pel search  (default: 9)
                         int       min_mcost,     // <--  minimum motion cost (cost for center or huge value)
                         double    lambda         // <--  lagrangian parameter for determining motion cost
                         )
{
  int   diff[16], *d;
  int   pos, best_pos, mcost, abort_search;
  int   y0, x0, ry0, rx0, ry;
  int   cand_mv_x, cand_mv_y;
  pel_t *orig_line;
  int   incr            = ref==-1 ? ((!img->fld_type)&&/*(!img->picture_structure)&&*/(img->type==B_IMG)) : (mref==mref_fld)&&(img->type==B_IMG) ;  //by oliver 0511
  pel_t **ref_pic;      
  int   lambda_factor   = LAMBDA_FACTOR (lambda);
  int   mv_shift        = 0;
  int   check_position0 = (blocktype==1 && *mv_x==0 && *mv_y==0 && input->hadamard && !input->rdopt && img->type!=B_IMG && ref==0);
  int   blocksize_x     = input->blc_size[blocktype][0];
  int   blocksize_y     = input->blc_size[blocktype][1];
  int   pic4_pix_x      = (pic_pix_x << 2);
  int   pic4_pix_y      = (pic_pix_y << 2);
  int   max_pos_x4      = ((img->width -blocksize_x+1)<<2);
  int   max_pos_y4      = ((img->height-blocksize_y+1)<<2);
  int   min_pos2        = (input->hadamard ? 0 : 1);
  int   max_pos2        = (input->hadamard ? max(1,search_pos2) : search_pos2);
  
  int   curr_diff[MB_BLOCK_SIZE][MB_BLOCK_SIZE]; // for AVS 8x8 SATD calculation
  int   xx,yy,kk;                                // indicees for curr_diff

  if (!img->picture_structure)
  {
	  if (img->type==B_IMG)
	  {
		  incr = 2;
	  }
  }else
  {
	  if(img->type==B_IMG)
		  incr = 1;
  }

  ref_pic = img->type==B_IMG? mref [ref+incr] : mref [ref];
  
  /*********************************
   *****                       *****
   *****  HALF-PEL REFINEMENT  *****
   *****                       *****
   *********************************/
  //===== convert search center to quarter-pel units =====
  *mv_x <<= 2;
  *mv_y <<= 2;
  //===== set function for getting pixel values =====
  if ((pic4_pix_x + *mv_x > 1) && (pic4_pix_x + *mv_x < max_pos_x4 - 2) &&
      (pic4_pix_y + *mv_y > 1) && (pic4_pix_y + *mv_y < max_pos_y4 - 2)   )
  {
    PelY_14 = FastPelY_14;
  }
  else
  {
    PelY_14 = UMVPelY_14;
  }
  //===== loop over search positions =====
  for (best_pos = 0, pos = min_pos2; pos < max_pos2; pos++)
  {
    cand_mv_x = *mv_x + (spiral_search_x[pos] << 1);    // quarter-pel units
    cand_mv_y = *mv_y + (spiral_search_y[pos] << 1);    // quarter-pel units

    //----- set motion vector cost -----
    mcost = MV_COST (lambda_factor, mv_shift, cand_mv_x, cand_mv_y, pred_mv_x, pred_mv_y);
    if (check_position0 && pos==0)
    {
      mcost -= WEIGHTED_COST (lambda_factor, 16);
    }

    //----- add up SATD -----
    for (y0=0, abort_search=0; y0<blocksize_y && !abort_search; y0+=4)
    {
      ry0 = ((pic_pix_y+y0)<<2) + cand_mv_y;

      for (x0=0; x0<blocksize_x; x0+=4)
      {
        rx0 = ((pic_pix_x+x0)<<2) + cand_mv_x;
        d   = diff;

        orig_line = orig_pic [y0  ];    ry=ry0;
        *d++      = orig_line[x0  ]  -  PelY_14 (ref_pic, ry, rx0   );
        *d++      = orig_line[x0+1]  -  PelY_14 (ref_pic, ry, rx0+ 4);
        *d++      = orig_line[x0+2]  -  PelY_14 (ref_pic, ry, rx0+ 8);
        *d++      = orig_line[x0+3]  -  PelY_14 (ref_pic, ry, rx0+12);

        orig_line = orig_pic [y0+1];    ry=ry0+4;
        *d++      = orig_line[x0  ]  -  PelY_14 (ref_pic, ry, rx0   );
        *d++      = orig_line[x0+1]  -  PelY_14 (ref_pic, ry, rx0+ 4);
        *d++      = orig_line[x0+2]  -  PelY_14 (ref_pic, ry, rx0+ 8);
        *d++      = orig_line[x0+3]  -  PelY_14 (ref_pic, ry, rx0+12);

        orig_line = orig_pic [y0+2];    ry=ry0+8;
        *d++      = orig_line[x0  ]  -  PelY_14 (ref_pic, ry, rx0   );
        *d++      = orig_line[x0+1]  -  PelY_14 (ref_pic, ry, rx0+ 4);
        *d++      = orig_line[x0+2]  -  PelY_14 (ref_pic, ry, rx0+ 8);
        *d++      = orig_line[x0+3]  -  PelY_14 (ref_pic, ry, rx0+12);

        orig_line = orig_pic [y0+3];    ry=ry0+12;
        *d++      = orig_line[x0  ]  -  PelY_14 (ref_pic, ry, rx0   );
        *d++      = orig_line[x0+1]  -  PelY_14 (ref_pic, ry, rx0+ 4);
        *d++      = orig_line[x0+2]  -  PelY_14 (ref_pic, ry, rx0+ 8);
        *d        = orig_line[x0+3]  -  PelY_14 (ref_pic, ry, rx0+12);

				for (yy=y0,kk=0; yy<y0+4; yy++)
					for (xx=x0; xx<x0+4; xx++, kk++)
						curr_diff[yy][xx] = diff[kk];         
      }
    }

    mcost += find_sad_8x8(input->hadamard, blocksize_x, blocksize_y, 0, 0, curr_diff);   
    if (mcost < min_mcost)
    {
      min_mcost = mcost;
      best_pos  = pos;
    }
  }

  if (best_pos)
  {
    *mv_x += (spiral_search_x [best_pos] << 1);
    *mv_y += (spiral_search_y [best_pos] << 1);
  }

  /************************************
   *****                          *****
   *****  QUARTER-PEL REFINEMENT  *****
   *****                          *****
   ************************************/
  //===== set function for getting pixel values =====
  if ((pic4_pix_x + *mv_x > 1) && (pic4_pix_x + *mv_x < max_pos_x4 - 1) &&
      (pic4_pix_y + *mv_y > 1) && (pic4_pix_y + *mv_y < max_pos_y4 - 1)   )
  {
    PelY_14 = FastPelY_14;
  }
  else
  {
    PelY_14 = UMVPelY_14;
  }
  
  //===== loop over search positions =====
  for (best_pos = 0, pos = 1; pos < search_pos4; pos++)
  {
    cand_mv_x = *mv_x + spiral_search_x[pos];    // quarter-pel units
    cand_mv_y = *mv_y + spiral_search_y[pos];    // quarter-pel units

    //----- set motion vector cost -----
    mcost = MV_COST (lambda_factor, mv_shift, cand_mv_x, cand_mv_y, pred_mv_x, pred_mv_y);

    //----- add up SATD -----
    for (y0=0, abort_search=0; y0<blocksize_y && !abort_search; y0+=4)
    {
      ry0 = ((pic_pix_y+y0)<<2) + cand_mv_y;

      for (x0=0; x0<blocksize_x; x0+=4)
      {
        rx0 = ((pic_pix_x+x0)<<2) + cand_mv_x;
        d   = diff;

        orig_line = orig_pic [y0  ];    ry=ry0;
        *d++      = orig_line[x0  ]  -  PelY_14 (ref_pic, ry, rx0   );
        *d++      = orig_line[x0+1]  -  PelY_14 (ref_pic, ry, rx0+ 4);
        *d++      = orig_line[x0+2]  -  PelY_14 (ref_pic, ry, rx0+ 8);
        *d++      = orig_line[x0+3]  -  PelY_14 (ref_pic, ry, rx0+12);

        orig_line = orig_pic [y0+1];    ry=ry0+4;
        *d++      = orig_line[x0  ]  -  PelY_14 (ref_pic, ry, rx0   );
        *d++      = orig_line[x0+1]  -  PelY_14 (ref_pic, ry, rx0+ 4);
        *d++      = orig_line[x0+2]  -  PelY_14 (ref_pic, ry, rx0+ 8);
        *d++      = orig_line[x0+3]  -  PelY_14 (ref_pic, ry, rx0+12);

        orig_line = orig_pic [y0+2];    ry=ry0+8;
        *d++      = orig_line[x0  ]  -  PelY_14 (ref_pic, ry, rx0   );
        *d++      = orig_line[x0+1]  -  PelY_14 (ref_pic, ry, rx0+ 4);
        *d++      = orig_line[x0+2]  -  PelY_14 (ref_pic, ry, rx0+ 8);
        *d++      = orig_line[x0+3]  -  PelY_14 (ref_pic, ry, rx0+12);