2010-05-18 17:58:33 +02:00
|
|
|
/*
|
2010-09-09 14:16:39 +02:00
|
|
|
* Copyright (c) 2010 The WebM project authors. All Rights Reserved.
|
2010-05-18 17:58:33 +02:00
|
|
|
*
|
2010-06-18 18:39:21 +02:00
|
|
|
* Use of this source code is governed by a BSD-style license
|
2010-06-04 22:19:40 +02:00
|
|
|
* that can be found in the LICENSE file in the root of the source
|
|
|
|
|
* tree. An additional intellectual property rights grant can be found
|
2010-06-18 18:39:21 +02:00
|
|
|
* in the file PATENTS. All contributing project authors may
|
2010-06-04 22:19:40 +02:00
|
|
|
* be found in the AUTHORS file in the root of the source tree.
|
2010-05-18 17:58:33 +02:00
|
|
|
*/
|
|
|
|
|
|
2012-11-30 01:36:10 +01:00
|
|
|
#ifndef VP9_ENCODER_VP9_ENCODEMB_H_
|
|
|
|
|
#define VP9_ENCODER_VP9_ENCODEMB_H_
|
2010-05-18 17:58:33 +02:00
|
|
|
|
2012-12-23 16:20:10 +01:00
|
|
|
#include "./vpx_config.h"
|
2012-11-28 19:41:40 +01:00
|
|
|
#include "vp9/encoder/vp9_block.h"
|
2013-03-05 23:12:16 +01:00
|
|
|
#include "vp9/encoder/vp9_onyx_int.h"
|
2013-02-20 19:16:24 +01:00
|
|
|
#include "vp9/common/vp9_onyxc_int.h"
|
2010-05-18 17:58:33 +02:00
|
|
|
|
2012-07-14 00:21:29 +02:00
|
|
|
typedef struct {
|
|
|
|
|
MB_PREDICTION_MODE mode;
|
|
|
|
|
MV_REFERENCE_FRAME ref_frame;
|
|
|
|
|
MV_REFERENCE_FRAME second_ref_frame;
|
2012-06-26 01:23:58 +02:00
|
|
|
} MODE_DEFINITION;
|
|
|
|
|
|
|
|
|
|
|
2012-10-31 22:40:53 +01:00
|
|
|
struct VP9_ENCODER_RTCD;
|
2013-05-01 01:13:20 +02:00
|
|
|
#if !CONFIG_SB8X8
|
2013-02-20 19:16:24 +01:00
|
|
|
void vp9_encode_inter16x16(VP9_COMMON *const cm, MACROBLOCK *x,
|
|
|
|
|
int mb_row, int mb_col);
|
2013-05-01 01:13:20 +02:00
|
|
|
#endif
|
2010-05-18 17:58:33 +02:00
|
|
|
|
Spatial resamping of ZEROMV predictors
This patch allows coding frames using references of different
resolution, in ZEROMV mode. For compound prediction, either
reference may be scaled.
To test, I use the resize_test and enable WRITE_RECON_BUFFER
in vp9_onyxd_if.c. It's also useful to apply this patch to
test/i420_video_source.h:
--- a/test/i420_video_source.h
+++ b/test/i420_video_source.h
@@ -93,6 +93,7 @@ class I420VideoSource : public VideoSource {
virtual void FillFrame() {
// Read a frame from input_file.
+ if (frame_ != 3)
if (fread(img_->img_data, raw_sz_, 1, input_file_) == 0) {
limit_ = frame_;
}
This forces the frame that the resolution changes on to be coded
with no motion, only scaling, and improves the quality of the
result.
Change-Id: I1ee75d19a437ff801192f767fd02a36bcbd1d496
2013-02-25 05:55:14 +01:00
|
|
|
void vp9_encode_inter16x16y(MACROBLOCK *x, int mb_row, int mb_col);
|
2011-02-14 23:18:18 +01:00
|
|
|
|
2013-04-10 06:28:27 +02:00
|
|
|
void vp9_transform_sby_32x32(MACROBLOCK *x, BLOCK_SIZE_TYPE bsize);
|
|
|
|
|
void vp9_transform_sby_16x16(MACROBLOCK *x, BLOCK_SIZE_TYPE bsize);
|
|
|
|
|
void vp9_transform_sby_8x8(MACROBLOCK *x, BLOCK_SIZE_TYPE bsize);
|
|
|
|
|
void vp9_transform_sby_4x4(MACROBLOCK *x, BLOCK_SIZE_TYPE bsize);
|
|
|
|
|
void vp9_transform_sbuv_32x32(MACROBLOCK *x, BLOCK_SIZE_TYPE bsize);
|
|
|
|
|
void vp9_transform_sbuv_16x16(MACROBLOCK *x, BLOCK_SIZE_TYPE bsize);
|
|
|
|
|
void vp9_transform_sbuv_8x8(MACROBLOCK *x, BLOCK_SIZE_TYPE bsize);
|
|
|
|
|
void vp9_transform_sbuv_4x4(MACROBLOCK *x, BLOCK_SIZE_TYPE bsize);
|
2013-04-30 18:54:51 +02:00
|
|
|
|
|
|
|
|
void vp9_optimize_sby(VP9_COMMON *const cm, MACROBLOCK *x,
|
|
|
|
|
BLOCK_SIZE_TYPE bsize);
|
|
|
|
|
void vp9_optimize_sbuv(VP9_COMMON *const cm, MACROBLOCK *x,
|
|
|
|
|
BLOCK_SIZE_TYPE bsize);
|
32x32 transform for superblocks.
This adds Debargha's DCT/DWT hybrid and a regular 32x32 DCT, and adds
code all over the place to wrap that in the bitstream/encoder/decoder/RD.
Some implementation notes (these probably need careful review):
- token range is extended by 1 bit, since the value range out of this
transform is [-16384,16383].
- the coefficients coming out of the FDCT are manually scaled back by
1 bit, or else they won't fit in int16_t (they are 17 bits). Because
of this, the RD error scoring does not right-shift the MSE score by
two (unlike for 4x4/8x8/16x16).
- to compensate for this loss in precision, the quantizer is halved
also. This is currently a little hacky.
- FDCT and IDCT is double-only right now. Needs a fixed-point impl.
- There are no default probabilities for the 32x32 transform yet; I'm
simply using the 16x16 luma ones. A future commit will add newly
generated probabilities for all transforms.
- No ADST version. I don't think we'll add one for this level; if an
ADST is desired, transform-size selection can scale back to 16x16
or lower, and use an ADST at that level.
Additional notes specific to Debargha's DWT/DCT hybrid:
- coefficient scale is different for the top/left 16x16 (DCT-over-DWT)
block than for the rest (DWT pixel differences) of the block. Therefore,
RD error scoring isn't easily scalable between coefficient and pixel
domain. Thus, unfortunately, we need to compute the RD distortion in
the pixel domain until we figure out how to scale these appropriately.
Change-Id: I00386f20f35d7fabb19aba94c8162f8aee64ef2b
2012-12-07 23:45:05 +01:00
|
|
|
|
2013-05-01 01:13:20 +02:00
|
|
|
#if !CONFIG_SB8X8
|
2013-02-20 19:16:24 +01:00
|
|
|
void vp9_fidct_mb(VP9_COMMON *const cm, MACROBLOCK *x);
|
2013-05-01 01:13:20 +02:00
|
|
|
#endif
|
2012-11-08 20:03:00 +01:00
|
|
|
|
2013-04-23 17:26:10 +02:00
|
|
|
void vp9_subtract_block(int rows, int cols,
|
|
|
|
|
int16_t *diff_ptr, int diff_stride,
|
|
|
|
|
const uint8_t *src_ptr, int src_stride,
|
|
|
|
|
const uint8_t *pred_ptr, int pred_stride);
|
|
|
|
|
void vp9_subtract_sby(MACROBLOCK *x, BLOCK_SIZE_TYPE bsize);
|
|
|
|
|
void vp9_subtract_sbuv(MACROBLOCK *x, BLOCK_SIZE_TYPE bsize);
|
|
|
|
|
void vp9_subtract_sb(MACROBLOCK *xd, BLOCK_SIZE_TYPE bsize);
|
2012-08-21 02:45:36 +02:00
|
|
|
|
2012-12-19 00:31:19 +01:00
|
|
|
#endif // VP9_ENCODER_VP9_ENCODEMB_H_
|