1
0
mirror of https://github.com/FFmpeg/FFmpeg.git synced 2024-12-07 11:13:41 +02:00
FFmpeg/libavcodec/psymodel.c

157 lines
4.9 KiB
C
Raw Normal View History

/*
* audio encoder psychoacoustic model
* Copyright (C) 2008 Konstantin Shishkov
*
* This file is part of FFmpeg.
*
* FFmpeg is free software; you can redistribute it and/or
* modify it under the terms of the GNU Lesser General Public
* License as published by the Free Software Foundation; either
* version 2.1 of the License, or (at your option) any later version.
*
* FFmpeg is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
* Lesser General Public License for more details.
*
* You should have received a copy of the GNU Lesser General Public
* License along with FFmpeg; if not, write to the Free Software
* Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
*/
#include <string.h>
#include "avcodec.h"
#include "psymodel.h"
#include "iirfilter.h"
#include "libavutil/mem.h"
extern const FFPsyModel ff_aac_psy_model;
av_cold int ff_psy_init(FFPsyContext *ctx, AVCodecContext *avctx, int num_lens,
const uint8_t **bands, const int* num_bands,
int num_groups, const uint8_t *group_map)
{
int i, j, k = 0;
ctx->avctx = avctx;
ctx->ch = av_mallocz_array(sizeof(ctx->ch[0]), avctx->channels * 2);
ctx->group = av_mallocz_array(sizeof(ctx->group[0]), num_groups);
ctx->bands = av_malloc_array (sizeof(ctx->bands[0]), num_lens);
ctx->num_bands = av_malloc_array (sizeof(ctx->num_bands[0]), num_lens);
AAC encoder: improve SF range utilization This patch does 4 things, all of which interact and thus it woudln't be possible to commit them separately without causing either quality regressions or assertion failures. Fate comparison targets don't all reflect improvements in quality, yet listening tests show substantially improved quality and stability. 1. Increase SF range utilization. The spec requires SF delta values to be constrained within the range -60..60. The previous code was applying that range to the whole SF array and not only the deltas of consecutive values, because doing so requires smarter code: zeroing or otherwise skipping a band may invalidate lots of SF choices. This patch implements that logic to allow the coders to utilize the full dynamic range of scalefactors, increasing quality quite considerably, and fixing delta-SF-related assertion failures, since now the limitation is enforced rather than asserted. 2. PNS tweaks The previous modification makes big improvements in twoloop's efficiency, and every time that happens PNS logic needs to be tweaked accordingly to avoid it from stepping all over twoloop's decisions. This patch includes modifications of the sort. 3. Account for lowpass cutoff during PSY analysis The closer PSY's allocation is to final allocation the better the quality is, and given these modifications, twoloop is now very efficient at avoiding holes. Thus, to compute accurate thresholds, PSY needs to account for the lowpass applied implicitly during twoloop (by zeroing high bands). This patch makes twoloop set the cutoff in psymodel's context the first time it runs, and makes PSY account for it during threshold computation, making PE and threshold computations closer to the final allocation and thus achieving better subjective quality. 4. Tweaks to RC lambda tracking loop in relation to PNS Without this tweak some corner cases cause quality regressions. Basically, lambda needs to react faster to overall bitrate efficiency changes since now PNS can be quite successful in enforcing maximum bitrates, when PSY allocates too many bits to the lower bands, suppressing the signals RC logic uses to lower lambda in those cases and causing aggressive PNS. This tweak makes PNS much less aggressive, though it can still use some further tweaks. Also update MIPS specializations and adjust fuzz Also in lavc/mips/aacpsy_mips.h: remove trailing whitespace
2015-12-01 08:28:36 +02:00
ctx->cutoff = avctx->cutoff;
2015-05-31 14:54:55 +02:00
if (!ctx->ch || !ctx->group || !ctx->bands || !ctx->num_bands) {
ff_psy_end(ctx);
return AVERROR(ENOMEM);
}
memcpy(ctx->bands, bands, sizeof(ctx->bands[0]) * num_lens);
memcpy(ctx->num_bands, num_bands, sizeof(ctx->num_bands[0]) * num_lens);
/* assign channels to groups (with virtual channels for coupling) */
for (i = 0; i < num_groups; i++) {
/* NOTE: Add 1 to handle the AAC chan_config without modification.
* This has the side effect of allowing an array of 0s to map
* to one channel per group.
*/
ctx->group[i].num_ch = group_map[i] + 1;
for (j = 0; j < ctx->group[i].num_ch * 2; j++)
ctx->group[i].ch[j] = &ctx->ch[k++];
}
switch (ctx->avctx->codec_id) {
case AV_CODEC_ID_AAC:
ctx->model = &ff_aac_psy_model;
break;
}
if (ctx->model->init)
return ctx->model->init(ctx);
return 0;
}
FFPsyChannelGroup *ff_psy_find_group(FFPsyContext *ctx, int channel)
{
int i = 0, ch = 0;
while (ch <= channel)
ch += ctx->group[i++].num_ch;
return &ctx->group[i-1];
}
av_cold void ff_psy_end(FFPsyContext *ctx)
{
if (ctx->model && ctx->model->end)
ctx->model->end(ctx);
av_freep(&ctx->bands);
av_freep(&ctx->num_bands);
av_freep(&ctx->group);
av_freep(&ctx->ch);
}
typedef struct FFPsyPreprocessContext{
AVCodecContext *avctx;
float stereo_att;
struct FFIIRFilterCoeffs *fcoeffs;
struct FFIIRFilterState **fstate;
struct FFIIRFilterContext fiir;
}FFPsyPreprocessContext;
#define FILT_ORDER 4
av_cold struct FFPsyPreprocessContext* ff_psy_preprocess_init(AVCodecContext *avctx)
{
FFPsyPreprocessContext *ctx;
int i;
float cutoff_coeff = 0;
ctx = av_mallocz(sizeof(FFPsyPreprocessContext));
2015-05-31 14:54:55 +02:00
if (!ctx)
return NULL;
ctx->avctx = avctx;
AAC encoder: Extensive improvements This finalizes merging of the work in the patches in ticket #2686. Improvements to twoloop and RC logic are extensive. The non-exhaustive list of twoloop improvments includes: - Tweaks to distortion limits on the RD optimization phase of twoloop - Deeper search in twoloop - PNS information marking to let twoloop decide when to use it (turned out having the decision made separately wasn't working) - Tonal band detection and priorization - Better band energy conservation rules - Strict hole avoidance For rate control: - Use psymodel's bit allocation to allow proper use of the bit reservoir. Don't work against the bit reservoir by moving lambda in the opposite direction when psymodel decides to allocate more/less bits to a frame. - Retry the encode if the effective rate lies outside a reasonable margin of psymodel's allocation or the selected ABR. - Log average lambda at the end. Useful info for everyone, but especially for tuning of the various encoder constants that relate to lambda feedback. Psy: - Do not apply lowpass with a FIR filter, instead just let the coder zero bands above the cutoff. The FIR filter induces group delay, and while zeroing bands causes ripple, it's lost in the quantization noise. - Experimental VBR bit allocation code - Tweak automatic lowpass filter threshold to maximize audio bandwidth at all bitrates while still providing acceptable, stable quality. I/S: - Phase decision fixes. Unrelated to #2686, but the bugs only surfaced when the merge was finalized. Measure I/S band energy accounting for phase, and prevent I/S and M/S from being applied both. PNS: - Avoid marking short bands with PNS when they're part of a window group in which there's a large variation of energy from one window to the next. PNS can't preserve those and the effect is extremely noticeable. M/S: - Implement BMLD protection similar to the specified in ISO-IEC/13818:7-2003, Appendix C Section 6.1. Since M/S decision doesn't conform to section 6.1, a different method had to be implemented, but should provide equivalent protection. - Move the decision logic closer to the method specified in ISO-IEC/13818:7-2003, Appendix C Section 6.1. Specifically, make sure M/S needs less bits than dual stereo. - Don't apply M/S in bands that are using I/S Now, this of course needed adjustments in the compare targets and fuzz factors of the AAC encoder's fate tests, but if wondering why the targets go up (more distortion), consider the previous coder was using too many bits on LF content (far more than required by psy), and thus those signals will now be more distorted, not less. The extra distortion isn't audible though, I carried extensive ABX testing to make sure. A very similar patch was also extensively tested by Kamendo2 in the context of #2686.
2015-10-11 22:29:50 +02:00
/* AAC has its own LP method */
if (avctx->codec_id != AV_CODEC_ID_AAC) {
if (avctx->cutoff > 0)
cutoff_coeff = 2.0 * avctx->cutoff / avctx->sample_rate;
if (cutoff_coeff && cutoff_coeff < 0.98)
ctx->fcoeffs = ff_iir_filter_init_coeffs(avctx, FF_FILTER_TYPE_BUTTERWORTH,
FF_FILTER_MODE_LOWPASS, FILT_ORDER,
cutoff_coeff, 0.0, 0.0);
if (ctx->fcoeffs) {
ctx->fstate = av_mallocz(sizeof(ctx->fstate[0]) * avctx->channels);
for (i = 0; i < avctx->channels; i++)
ctx->fstate[i] = ff_iir_filter_init_state(FILT_ORDER);
}
AAC encoder: Extensive improvements This finalizes merging of the work in the patches in ticket #2686. Improvements to twoloop and RC logic are extensive. The non-exhaustive list of twoloop improvments includes: - Tweaks to distortion limits on the RD optimization phase of twoloop - Deeper search in twoloop - PNS information marking to let twoloop decide when to use it (turned out having the decision made separately wasn't working) - Tonal band detection and priorization - Better band energy conservation rules - Strict hole avoidance For rate control: - Use psymodel's bit allocation to allow proper use of the bit reservoir. Don't work against the bit reservoir by moving lambda in the opposite direction when psymodel decides to allocate more/less bits to a frame. - Retry the encode if the effective rate lies outside a reasonable margin of psymodel's allocation or the selected ABR. - Log average lambda at the end. Useful info for everyone, but especially for tuning of the various encoder constants that relate to lambda feedback. Psy: - Do not apply lowpass with a FIR filter, instead just let the coder zero bands above the cutoff. The FIR filter induces group delay, and while zeroing bands causes ripple, it's lost in the quantization noise. - Experimental VBR bit allocation code - Tweak automatic lowpass filter threshold to maximize audio bandwidth at all bitrates while still providing acceptable, stable quality. I/S: - Phase decision fixes. Unrelated to #2686, but the bugs only surfaced when the merge was finalized. Measure I/S band energy accounting for phase, and prevent I/S and M/S from being applied both. PNS: - Avoid marking short bands with PNS when they're part of a window group in which there's a large variation of energy from one window to the next. PNS can't preserve those and the effect is extremely noticeable. M/S: - Implement BMLD protection similar to the specified in ISO-IEC/13818:7-2003, Appendix C Section 6.1. Since M/S decision doesn't conform to section 6.1, a different method had to be implemented, but should provide equivalent protection. - Move the decision logic closer to the method specified in ISO-IEC/13818:7-2003, Appendix C Section 6.1. Specifically, make sure M/S needs less bits than dual stereo. - Don't apply M/S in bands that are using I/S Now, this of course needed adjustments in the compare targets and fuzz factors of the AAC encoder's fate tests, but if wondering why the targets go up (more distortion), consider the previous coder was using too many bits on LF content (far more than required by psy), and thus those signals will now be more distorted, not less. The extra distortion isn't audible though, I carried extensive ABX testing to make sure. A very similar patch was also extensively tested by Kamendo2 in the context of #2686.
2015-10-11 22:29:50 +02:00
}
ff_iir_filter_init(&ctx->fiir);
return ctx;
}
void ff_psy_preprocess(struct FFPsyPreprocessContext *ctx, float **audio, int channels)
{
int ch;
int frame_size = ctx->avctx->frame_size;
FFIIRFilterContext *iir = &ctx->fiir;
if (ctx->fstate) {
for (ch = 0; ch < channels; ch++)
iir->filter_flt(ctx->fcoeffs, ctx->fstate[ch], frame_size,
&audio[ch][frame_size], 1, &audio[ch][frame_size], 1);
}
}
av_cold void ff_psy_preprocess_end(struct FFPsyPreprocessContext *ctx)
{
int i;
ff_iir_filter_free_coeffsp(&ctx->fcoeffs);
if (ctx->fstate)
for (i = 0; i < ctx->avctx->channels; i++)
ff_iir_filter_free_statep(&ctx->fstate[i]);
av_freep(&ctx->fstate);
av_free(ctx);
}