vpx/vp8/encoder/mcomp.h

150 lines
4.3 KiB
C
Raw Normal View History

2010-05-18 17:58:33 +02:00
/*
* Copyright (c) 2010 The WebM project authors. All Rights Reserved.
2010-05-18 17:58:33 +02:00
*
* Use of this source code is governed by a BSD-style license
* that can be found in the LICENSE file in the root of the source
* tree. An additional intellectual property rights grant can be found
* in the file PATENTS. All contributing project authors may
* be found in the AUTHORS file in the root of the source tree.
2010-05-18 17:58:33 +02:00
*/
#ifndef __INC_MCOMP_H
#define __INC_MCOMP_H
#include "block.h"
#include "variance.h"
#ifdef ENTROPY_STATS
extern void init_mv_ref_counts();
extern void accum_mv_refs(MB_PREDICTION_MODE, const int near_mv_ref_cts[4]);
#endif
#define MAX_MVSEARCH_STEPS 8 // The maximum number of steps in a step search given the largest allowed initial step
#define MAX_FULL_PEL_VAL ((1 << (MAX_MVSEARCH_STEPS)) - 1) // Max full pel mv specified in 1 pel units
2010-05-18 17:58:33 +02:00
#define MAX_FIRST_STEP (1 << (MAX_MVSEARCH_STEPS-1)) // Maximum size of the first step in full pel units
WebM Experimental Codec Branch Snapshot This is a code snapshot of experimental work currently ongoing for a next-generation codec. The codebase has been cut down considerably from the libvpx baseline. For example, we are currently only supporting VBR 2-pass rate control and have removed most of the code relating to coding speed, threading, error resilience, partitions and various other features. This is in part to make the codebase easier to work on and experiment with, but also because we want to have an open discussion about how the bitstream will be structured and partitioned and not have that conversation constrained by past work. Our basic working pattern has been to initially encapsulate experiments using configure options linked to #IF CONFIG_XXX statements in the code. Once experiments have matured and we are reasonably happy that they give benefit and can be merged without breaking other experiments, we remove the conditional compile statements and merge them in. Current changes include: * Temporal coding experiment for segments (though still only 4 max, it will likely be increased). * Segment feature experiment - to allow various bits of information to be coded at the segment level. Features tested so far include mode and reference frame information, limiting end of block offset and transform size, alongside Q and loop filter parameters, but this set is very fluid. * Support for 8x8 transform - 8x8 dct with 2nd order 2x2 haar is used in MBs using 16x16 prediction modes within inter frames. * Compound prediction (combination of signals from existing predictors to create a new predictor). * 8 tap interpolation filters and 1/8th pel motion vectors. * Loop filter modifications. * Various entropy modifications and changes to how entropy contexts and updates are handled. * Extended quantizer range matched to transform precision improvements. There are also ongoing further experiments that we hope to merge in the near future: For example, coding of motion and other aspects of the prediction signal to better support larger image formats, use of larger block sizes (e.g. 32x32 and up) and lossless non-transform based coding options (especially for key frames). It is our hope that we will be able to make regular updates and we will warmly welcome community contributions. Please be warned that, at this stage, the codebase is currently slower than VP8 stable branch as most new code has not been optimized, and even the 'C' has been deliberately written to be simple and obvious, not fast. The following graphs have the initial test results, numbers in the tables measure the compression improvement in terms of percentage. The build has the following optional experiments configured: --enable-experimental --enable-enhanced_interp --enable-uvintra --enable-high_precision_mv --enable-sixteenth_subpel_uv CIF Size clips: http://getwebm.org/tmp/cif/ HD size clips: http://getwebm.org/tmp/hd/ (stable_20120309 represents encoding results of WebM master branch build as of commit#7a15907) They were encoded using the following encode parameters: --good --cpu-used=0 -t 0 --lag-in-frames=25 --min-q=0 --max-q=63 --end-usage=0 --auto-alt-ref=1 -p 2 --pass=2 --kf-max-dist=9999 --kf-min-dist=0 --drop-frame=0 --static-thresh=0 --bias-pct=50 --minsection-pct=0 --maxsection-pct=800 --sharpness=0 --arnr-maxframes=7 --arnr-strength=3(for HD,6 for CIF) --arnr-type=3 Change-Id: I5c62ed09cfff5815a2bb34e7820d6a810c23183c
2012-03-10 02:32:50 +01:00
#if CONFIG_HIGH_PRECISION_MV
extern int vp8_mv_bit_cost(int_mv *mv, int_mv *ref, int *mvcost[2], int Weight, int ishp);
#else
extern int vp8_mv_bit_cost(int_mv *mv, int_mv *ref, int *mvcost[2], int Weight);
WebM Experimental Codec Branch Snapshot This is a code snapshot of experimental work currently ongoing for a next-generation codec. The codebase has been cut down considerably from the libvpx baseline. For example, we are currently only supporting VBR 2-pass rate control and have removed most of the code relating to coding speed, threading, error resilience, partitions and various other features. This is in part to make the codebase easier to work on and experiment with, but also because we want to have an open discussion about how the bitstream will be structured and partitioned and not have that conversation constrained by past work. Our basic working pattern has been to initially encapsulate experiments using configure options linked to #IF CONFIG_XXX statements in the code. Once experiments have matured and we are reasonably happy that they give benefit and can be merged without breaking other experiments, we remove the conditional compile statements and merge them in. Current changes include: * Temporal coding experiment for segments (though still only 4 max, it will likely be increased). * Segment feature experiment - to allow various bits of information to be coded at the segment level. Features tested so far include mode and reference frame information, limiting end of block offset and transform size, alongside Q and loop filter parameters, but this set is very fluid. * Support for 8x8 transform - 8x8 dct with 2nd order 2x2 haar is used in MBs using 16x16 prediction modes within inter frames. * Compound prediction (combination of signals from existing predictors to create a new predictor). * 8 tap interpolation filters and 1/8th pel motion vectors. * Loop filter modifications. * Various entropy modifications and changes to how entropy contexts and updates are handled. * Extended quantizer range matched to transform precision improvements. There are also ongoing further experiments that we hope to merge in the near future: For example, coding of motion and other aspects of the prediction signal to better support larger image formats, use of larger block sizes (e.g. 32x32 and up) and lossless non-transform based coding options (especially for key frames). It is our hope that we will be able to make regular updates and we will warmly welcome community contributions. Please be warned that, at this stage, the codebase is currently slower than VP8 stable branch as most new code has not been optimized, and even the 'C' has been deliberately written to be simple and obvious, not fast. The following graphs have the initial test results, numbers in the tables measure the compression improvement in terms of percentage. The build has the following optional experiments configured: --enable-experimental --enable-enhanced_interp --enable-uvintra --enable-high_precision_mv --enable-sixteenth_subpel_uv CIF Size clips: http://getwebm.org/tmp/cif/ HD size clips: http://getwebm.org/tmp/hd/ (stable_20120309 represents encoding results of WebM master branch build as of commit#7a15907) They were encoded using the following encode parameters: --good --cpu-used=0 -t 0 --lag-in-frames=25 --min-q=0 --max-q=63 --end-usage=0 --auto-alt-ref=1 -p 2 --pass=2 --kf-max-dist=9999 --kf-min-dist=0 --drop-frame=0 --static-thresh=0 --bias-pct=50 --minsection-pct=0 --maxsection-pct=800 --sharpness=0 --arnr-maxframes=7 --arnr-strength=3(for HD,6 for CIF) --arnr-type=3 Change-Id: I5c62ed09cfff5815a2bb34e7820d6a810c23183c
2012-03-10 02:32:50 +01:00
#endif
2010-05-18 17:58:33 +02:00
extern void vp8_init_dsmotion_compensation(MACROBLOCK *x, int stride);
extern void vp8_init3smotion_compensation(MACROBLOCK *x, int stride);
extern int vp8_hex_search
(
MACROBLOCK *x,
BLOCK *b,
BLOCKD *d,
int_mv *ref_mv,
int_mv *best_mv,
int search_param,
int error_per_bit,
const vp8_variance_fn_ptr_t *vf,
int *mvsadcost[2],
int *mvcost[2],
int_mv *center_mv
2010-05-18 17:58:33 +02:00
);
typedef int (fractional_mv_step_fp)
(MACROBLOCK *x, BLOCK *b, BLOCKD *d, int_mv *bestmv, int_mv *ref_mv,
int error_per_bit, const vp8_variance_fn_ptr_t *vfp, int *mvcost[2],
int *distortion, unsigned int *sse);
2010-05-18 17:58:33 +02:00
extern fractional_mv_step_fp vp8_find_best_sub_pixel_step_iteratively;
extern fractional_mv_step_fp vp8_find_best_sub_pixel_step;
extern fractional_mv_step_fp vp8_find_best_half_pixel_step;
extern fractional_mv_step_fp vp8_skip_fractional_mv_step;
#define prototype_full_search_sad(sym)\
int (sym)\
(\
MACROBLOCK *x, \
BLOCK *b, \
BLOCKD *d, \
int_mv *ref_mv, \
int sad_per_bit, \
int distance, \
vp8_variance_fn_ptr_t *fn_ptr, \
int *mvcost[2], \
int_mv *center_mv \
)
2010-05-18 17:58:33 +02:00
#define prototype_refining_search_sad(sym)\
int (sym)\
(\
MACROBLOCK *x, \
BLOCK *b, \
BLOCKD *d, \
int_mv *ref_mv, \
int sad_per_bit, \
int distance, \
vp8_variance_fn_ptr_t *fn_ptr, \
int *mvcost[2], \
int_mv *center_mv \
)
2010-05-18 17:58:33 +02:00
#define prototype_diamond_search_sad(sym)\
int (sym)\
(\
MACROBLOCK *x, \
BLOCK *b, \
BLOCKD *d, \
int_mv *ref_mv, \
int_mv *best_mv, \
int search_param, \
int sad_per_bit, \
int *num00, \
vp8_variance_fn_ptr_t *fn_ptr, \
int *mvcost[2], \
int_mv *center_mv \
)
2010-05-18 17:58:33 +02:00
#if ARCH_X86 || ARCH_X86_64
#include "x86/mcomp_x86.h"
#endif
typedef prototype_full_search_sad(*vp8_full_search_fn_t);
extern prototype_full_search_sad(vp8_full_search_sad);
extern prototype_full_search_sad(vp8_full_search_sadx3);
extern prototype_full_search_sad(vp8_full_search_sadx8);
2010-05-18 17:58:33 +02:00
typedef prototype_refining_search_sad(*vp8_refining_search_fn_t);
extern prototype_refining_search_sad(vp8_refining_search_sad);
extern prototype_refining_search_sad(vp8_refining_search_sadx4);
2010-05-18 17:58:33 +02:00
typedef prototype_diamond_search_sad(*vp8_diamond_search_fn_t);
extern prototype_diamond_search_sad(vp8_diamond_search_sad);
extern prototype_diamond_search_sad(vp8_diamond_search_sadx4);
#ifndef vp8_search_full_search
#define vp8_search_full_search vp8_full_search_sad
#endif
extern prototype_full_search_sad(vp8_search_full_search);
#ifndef vp8_search_refining_search
#define vp8_search_refining_search vp8_refining_search_sad
#endif
extern prototype_refining_search_sad(vp8_search_refining_search);
2010-05-18 17:58:33 +02:00
#ifndef vp8_search_diamond_search
#define vp8_search_diamond_search vp8_diamond_search_sad
#endif
extern prototype_diamond_search_sad(vp8_search_diamond_search);
typedef struct {
prototype_full_search_sad(*full_search);
prototype_refining_search_sad(*refining_search);
prototype_diamond_search_sad(*diamond_search);
2010-05-18 17:58:33 +02:00
} vp8_search_rtcd_vtable_t;
#if CONFIG_RUNTIME_CPU_DETECT
#define SEARCH_INVOKE(ctx,fn) (ctx)->fn
#else
#define SEARCH_INVOKE(ctx,fn) vp8_search_##fn
#endif
#endif