vpx/vp9/encoder/vp9_tokenize.h

138 lines
4.2 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 VP9_ENCODER_VP9_TOKENIZE_H_
#define VP9_ENCODER_VP9_TOKENIZE_H_
2010-05-18 17:58:33 +02:00
#include "vp9/common/vp9_entropy.h"
#include "vp9/encoder/vp9_block.h"
#include "vp9/encoder/vp9_treewriter.h"
2010-05-18 17:58:33 +02:00
#ifdef __cplusplus
extern "C" {
#endif
#define EOSB_TOKEN 127 // Not signalled, encoder only
#if CONFIG_VP9_HIGHBITDEPTH
typedef int32_t EXTRABIT;
#else
typedef int16_t EXTRABIT;
#endif
typedef struct {
int16_t token;
EXTRABIT extra;
} TOKENVALUE;
typedef struct {
const vpx_prob *context_tree;
int16_t token;
EXTRABIT extra;
2010-05-18 17:58:33 +02:00
} TOKENEXTRA;
extern const vpx_tree_index vp9_coef_tree[];
extern const vpx_tree_index vp9_coef_con_tree[];
extern const struct vp9_token vp9_coef_encodings[];
int vp9_is_skippable_in_plane(MACROBLOCK *x, BLOCK_SIZE bsize, int plane);
int vp9_has_high_freq_in_plane(MACROBLOCK *x, BLOCK_SIZE bsize, int plane);
struct VP9_COMP;
struct ThreadData;
void vp9_tokenize_sb(struct VP9_COMP *cpi, struct ThreadData *td,
TOKENEXTRA **t, int dry_run, int seg_skip,
BLOCK_SIZE bsize);
typedef struct {
const vpx_prob *prob;
int len;
int base_val;
const int16_t *cost;
} vp9_extra_bit;
// indexed by token value
extern const vp9_extra_bit vp9_extra_bits[ENTROPY_TOKENS];
#if CONFIG_VP9_HIGHBITDEPTH
extern const vp9_extra_bit vp9_extra_bits_high10[ENTROPY_TOKENS];
extern const vp9_extra_bit vp9_extra_bits_high12[ENTROPY_TOKENS];
#endif // CONFIG_VP9_HIGHBITDEPTH
extern const int16_t *vp9_dct_value_cost_ptr;
Add trellis quantization. Replace the exponential search for optimal rounding during quantization with a linear Viterbi trellis and enable it by default when using --best. Right now this operates on top of the output of the adaptive zero-bin quantizer in vp8_regular_quantize_b() and gives a small gain. It can be tested as a replacement for that quantizer by enabling the call to vp8_strict_quantize_b(), which uses normal rounding and no zero bin offset. Ultimately, the quantizer will have to become a function of lambda in order to take advantage of activity masking, since there is limited ability to change the quantization factor itself. However, currently vp8_strict_quantize_b() plus the trellis quantizer (which is lambda-dependent) loses to vp8_regular_quantize_b() alone (which is not) on my test clip. Patch Set 3: Fix an issue related to the cost evaluation of successor states when a coefficient is reduced to zero. With this issue fixed, now the trellis search almost exactly matches the exponential search. Patch Set 2: Overall, the goal of this patch set is to make "trellis" search to produce encodings that match the exponential search version. There are three main differences between Patch Set 2 and 1: a. Patch set 1 did not properly account for the scale of 2nd order error, so patch set 2 disable it all together for 2nd blocks. b. Patch set 1 was not consistent on when to enable the the quantization optimization. Patch set 2 restore the condition to be consistent. c. Patch set 1 checks quantized level L-1, and L for any input coefficient was quantized to L. Patch set 2 limits the candidate coefficient to those that were rounded up to L. It is worth noting here that a strategy to check L and L+1 for coefficients that were truncated down to L might work. (a and b get trellis quant to basically match the exponential search on all mid/low rate encodings on cif set, without a, b, trellis quant can hurt the psnr by 0.2 to .3db at 200kbps for some cif clips) (c gets trellis quant to match the exponential search to match at Q0 encoding, without c, trellis quant can be 1.5 to 2db lower for encodings with fixed Q at 0 on most derf cif clips) Change-Id: Ib1a043b665d75fbf00cb0257b7c18e90eebab95e
2010-07-02 23:35:53 +02:00
/* TODO: The Token field should be broken out into a separate char array to
* improve cache locality, since it's needed for costing when the rest of the
* fields are not.
*/
extern const TOKENVALUE *vp9_dct_value_tokens_ptr;
extern const TOKENVALUE *vp9_dct_cat_lt_10_value_tokens;
extern const int *vp9_dct_cat_lt_10_value_cost;
extern const int16_t vp9_cat6_low_cost[256];
extern const int vp9_cat6_high_cost[64];
extern const int vp9_cat6_high10_high_cost[256];
extern const int vp9_cat6_high12_high_cost[1024];
static INLINE int vp9_get_cost(int16_t token, EXTRABIT extrabits,
const int *cat6_high_table) {
if (token != CATEGORY6_TOKEN)
return vp9_extra_bits[token].cost[extrabits >> 1];
return vp9_cat6_low_cost[(extrabits >> 1) & 0xff] +
cat6_high_table[extrabits >> 9];
}
#if CONFIG_VP9_HIGHBITDEPTH
static INLINE const int *vp9_get_high_cost_table(int bit_depth) {
return bit_depth == 8 ? vp9_cat6_high_cost
: (bit_depth == 10 ? vp9_cat6_high10_high_cost
: vp9_cat6_high12_high_cost);
}
#else
static INLINE const int *vp9_get_high_cost_table(int bit_depth) {
(void)bit_depth;
return vp9_cat6_high_cost;
}
#endif // CONFIG_VP9_HIGHBITDEPTH
2010-05-18 17:58:33 +02:00
static INLINE void vp9_get_token_extra(int v, int16_t *token, EXTRABIT *extra) {
if (v >= CAT6_MIN_VAL || v <= -CAT6_MIN_VAL) {
*token = CATEGORY6_TOKEN;
if (v >= CAT6_MIN_VAL)
*extra = 2 * v - 2 * CAT6_MIN_VAL;
else
*extra = -2 * v - 2 * CAT6_MIN_VAL + 1;
return;
}
*token = vp9_dct_cat_lt_10_value_tokens[v].token;
*extra = vp9_dct_cat_lt_10_value_tokens[v].extra;
}
static INLINE int16_t vp9_get_token(int v) {
if (v >= CAT6_MIN_VAL || v <= -CAT6_MIN_VAL) return 10;
return vp9_dct_cat_lt_10_value_tokens[v].token;
}
static INLINE int vp9_get_token_cost(int v, int16_t *token,
const int *cat6_high_table) {
if (v >= CAT6_MIN_VAL || v <= -CAT6_MIN_VAL) {
EXTRABIT extrabits;
*token = CATEGORY6_TOKEN;
extrabits = abs(v) - CAT6_MIN_VAL;
return vp9_cat6_low_cost[extrabits & 0xff] +
cat6_high_table[extrabits >> 8];
}
*token = vp9_dct_cat_lt_10_value_tokens[v].token;
return vp9_dct_cat_lt_10_value_cost[v];
}
#ifdef __cplusplus
} // extern "C"
#endif
#endif // VP9_ENCODER_VP9_TOKENIZE_H_