added a last stage rounding for 8x8 inverse dct
Prior to the added rounding, tests on randomly generated data showed that forward-inverse transform round trip errors are about 3.02/block for input range [-10,10] and 2.68/block for input range [-256, 255]. The added rounding reduced the errors to 0.031/block for input range [-10,10] and 0.037/block for input range [-256, 255]. Maximum round trip error on for any pixel position is 1. The average errors are calculated based on 100,000 blocks of randomly with the specified ranges. Paul mentioned in discussion that the change was not clear on why we need change the rounding, so Patch 2 intends to make the rationale obvious in code, it merged the two separate shifts into one, and the two separate rounding factors into one. Patch 1 and 2 have same numerical test results. Change-Id: Ic5e2f5463de17253084d8b2398c4a210194b20de
This commit is contained in:
Родитель
152ce6b2b9
Коммит
a66c945c59
|
@ -369,7 +369,7 @@ static void idctcol (int *blk)
|
|||
((blk[8 * 0] + 32) >> 6);
|
||||
return;
|
||||
}
|
||||
x0 = (blk[8 * 0] << 8) + 8192;
|
||||
x0 = (blk[8 * 0] << 8) + 16384;
|
||||
|
||||
/* first stage */
|
||||
x8 = W7 * (x4 + x5) + 4;
|
||||
|
@ -399,14 +399,14 @@ static void idctcol (int *blk)
|
|||
x4 = (181 * (x4 - x5) + 128) >> 8;
|
||||
|
||||
/* fourth stage */
|
||||
blk[8 * 0] = (x7 + x1) >> 14;
|
||||
blk[8 * 1] = (x3 + x2) >> 14;
|
||||
blk[8 * 2] = (x0 + x4) >> 14;
|
||||
blk[8 * 3] = (x8 + x6) >> 14;
|
||||
blk[8 * 4] = (x8 - x6) >> 14;
|
||||
blk[8 * 5] = (x0 - x4) >> 14;
|
||||
blk[8 * 6] = (x3 - x2) >> 14;
|
||||
blk[8 * 7] = (x7 - x1) >> 14;
|
||||
blk[8 * 0] = (x7 + x1 ) >> 15;
|
||||
blk[8 * 1] = (x3 + x2 ) >> 15;
|
||||
blk[8 * 2] = (x0 + x4 ) >> 15;
|
||||
blk[8 * 3] = (x8 + x6 ) >> 15;
|
||||
blk[8 * 4] = (x8 - x6 ) >> 15;
|
||||
blk[8 * 5] = (x0 - x4 ) >> 15;
|
||||
blk[8 * 6] = (x3 - x2 ) >> 15;
|
||||
blk[8 * 7] = (x7 - x1 ) >> 15;
|
||||
}
|
||||
|
||||
#define TX_DIM 8
|
||||
|
@ -434,7 +434,7 @@ void vp8_short_idct8x8_c(short *coefs, short *block, int pitch)
|
|||
{
|
||||
for (j = 0; j < TX_DIM; j++)
|
||||
{
|
||||
block[i*shortpitch+j] = X[i * TX_DIM + j]>>1;
|
||||
block[i*shortpitch+j] = X[i * TX_DIM + j];
|
||||
}
|
||||
}
|
||||
}
|
||||
|
|
Загрузка…
Ссылка в новой задаче