FFmpeg
af_stereowiden.c
Go to the documentation of this file.
1 /*
2  * Copyright (C) 2012 VLC authors and VideoLAN
3  * Author : Sukrit Sangwan < sukritsangwan at gmail dot com >
4  *
5  * This file is part of FFmpeg.
6  *
7  * FFmpeg is free software; you can redistribute it and/or
8  * modify it under the terms of the GNU Lesser General Public
9  * License as published by the Free Software Foundation; either
10  * version 2.1 of the License, or (at your option) any later version.
11  *
12  * FFmpeg is distributed in the hope that it will be useful,
13  * but WITHOUT ANY WARRANTY; without even the implied warranty of
14  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
15  * Lesser General Public License for more details.
16  *
17  * You should have received a copy of the GNU Lesser General Public
18  * License along with FFmpeg; if not, write to the Free Software
19  * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
20  */
21 
23 #include "libavutil/opt.h"
24 #include "avfilter.h"
25 #include "audio.h"
26 #include "formats.h"
27 
28 typedef struct StereoWidenContext {
29  const AVClass *class;
30 
31  float delay;
32  float feedback;
33  float crossfeed;
34  float drymix;
35 
36  float *buffer;
37  float *cur;
38  int length;
40 
41 #define OFFSET(x) offsetof(StereoWidenContext, x)
42 #define A AV_OPT_FLAG_AUDIO_PARAM|AV_OPT_FLAG_FILTERING_PARAM
43 
44 static const AVOption stereowiden_options[] = {
45  { "delay", "set delay time", OFFSET(delay), AV_OPT_TYPE_FLOAT, {.dbl=20}, 1, 100, A },
46  { "feedback", "set feedback gain", OFFSET(feedback), AV_OPT_TYPE_FLOAT, {.dbl=.3}, 0, 0.9, A },
47  { "crossfeed", "set cross feed", OFFSET(crossfeed), AV_OPT_TYPE_FLOAT, {.dbl=.3}, 0, 0.8, A },
48  { "drymix", "set dry-mix", OFFSET(drymix), AV_OPT_TYPE_FLOAT, {.dbl=.8}, 0, 1.0, A },
49  { NULL }
50 };
51 
52 AVFILTER_DEFINE_CLASS(stereowiden);
53 
55 {
58  int ret;
59 
60  if ((ret = ff_add_format (&formats, AV_SAMPLE_FMT_FLT )) < 0 ||
61  (ret = ff_set_common_formats (ctx , formats )) < 0 ||
64  return ret;
65 
68 }
69 
71 {
72  AVFilterContext *ctx = inlink->dst;
73  StereoWidenContext *s = ctx->priv;
74 
75  s->length = s->delay * inlink->sample_rate / 1000;
76  s->length *= 2;
77  s->buffer = av_calloc(s->length, sizeof(*s->buffer));
78  if (!s->buffer)
79  return AVERROR(ENOMEM);
80  s->cur = s->buffer;
81 
82  return 0;
83 }
84 
86 {
87  AVFilterContext *ctx = inlink->dst;
88  AVFilterLink *outlink = ctx->outputs[0];
89  StereoWidenContext *s = ctx->priv;
90  const float *src = (const float *)in->data[0];
91  const float drymix = s->drymix;
92  const float crossfeed = s->crossfeed;
93  const float feedback = s->feedback;
94  AVFrame *out;
95  float *dst;
96  int n;
97 
99  out = in;
100  } else {
101  out = ff_get_audio_buffer(outlink, in->nb_samples);
102  if (!out) {
103  av_frame_free(&in);
104  return AVERROR(ENOMEM);
105  }
107  }
108  dst = (float *)out->data[0];
109 
110  for (n = 0; n < in->nb_samples; n++, src += 2, dst += 2, s->cur += 2) {
111  const float left = src[0], right = src[1];
112 
113  if (s->cur == s->buffer + s->length)
114  s->cur = s->buffer;
115 
116  if (ctx->is_disabled) {
117  dst[0] = left;
118  dst[1] = right;
119  } else {
120  dst[0] = drymix * left - crossfeed * right - feedback * s->cur[1];
121  dst[1] = drymix * right - crossfeed * left - feedback * s->cur[0];
122  }
123 
124  s->cur[0] = left;
125  s->cur[1] = right;
126  }
127 
128  if (out != in)
129  av_frame_free(&in);
130  return ff_filter_frame(outlink, out);
131 }
132 
134 {
135  StereoWidenContext *s = ctx->priv;
136 
137  av_freep(&s->buffer);
138 }
139 
140 static const AVFilterPad inputs[] = {
141  {
142  .name = "default",
143  .type = AVMEDIA_TYPE_AUDIO,
144  .filter_frame = filter_frame,
145  .config_props = config_input,
146  },
147  { NULL }
148 };
149 
150 static const AVFilterPad outputs[] = {
151  {
152  .name = "default",
153  .type = AVMEDIA_TYPE_AUDIO,
154  },
155  { NULL }
156 };
157 
159  .name = "stereowiden",
160  .description = NULL_IF_CONFIG_SMALL("Apply stereo widening effect."),
161  .query_formats = query_formats,
162  .priv_size = sizeof(StereoWidenContext),
163  .priv_class = &stereowiden_class,
164  .uninit = uninit,
165  .inputs = inputs,
166  .outputs = outputs,
168 };
formats
formats
Definition: signature.h:48
ff_get_audio_buffer
AVFrame * ff_get_audio_buffer(AVFilterLink *link, int nb_samples)
Request an audio samples buffer with a specific set of permissions.
Definition: audio.c:86
AVFilterChannelLayouts
A list of supported channel layouts.
Definition: formats.h:85
AVERROR
Filter the word “frame” indicates either a video frame or a group of audio as stored in an AVFrame structure Format for each input and each output the list of supported formats For video that means pixel format For audio that means channel sample they are references to shared objects When the negotiation mechanism computes the intersection of the formats supported at each end of a all references to both lists are replaced with a reference to the intersection And when a single format is eventually chosen for a link amongst the remaining all references to the list are updated That means that if a filter requires that its input and output have the same format amongst a supported all it has to do is use a reference to the same list of formats query_formats can leave some formats unset and return AVERROR(EAGAIN) to cause the negotiation mechanism toagain later. That can be used by filters with complex requirements to use the format negotiated on one link to set the formats supported on another. Frame references ownership and permissions
opt.h
out
FILE * out
Definition: movenc.c:54
uninit
static av_cold void uninit(AVFilterContext *ctx)
Definition: af_stereowiden.c:133
n
int n
Definition: avisynth_c.h:760
A
#define A
Definition: af_stereowiden.c:42
ff_set_common_channel_layouts
int ff_set_common_channel_layouts(AVFilterContext *ctx, AVFilterChannelLayouts *layouts)
A helper for query_formats() which sets all links to the same list of channel layouts/sample rates.
Definition: formats.c:549
ff_filter_frame
int ff_filter_frame(AVFilterLink *link, AVFrame *frame)
Send a frame of data to the next filter.
Definition: avfilter.c:1080
inlink
The exact code depends on how similar the blocks are and how related they are to the and needs to apply these operations to the correct inlink or outlink if there are several Macros are available to factor that when no extra processing is inlink
Definition: filter_design.txt:212
av_frame_free
void av_frame_free(AVFrame **frame)
Free the frame and any dynamically allocated objects in it, e.g.
Definition: frame.c:202
inputs
static const AVFilterPad inputs[]
Definition: af_stereowiden.c:140
AVFrame
This structure describes decoded (raw) audio or video data.
Definition: frame.h:295
AVOption
AVOption.
Definition: opt.h:246
AVFilter::name
const char * name
Filter name.
Definition: avfilter.h:148
AVFilterFormats
A list of supported formats for one end of a filter link.
Definition: formats.h:64
formats.h
StereoWidenContext::feedback
float feedback
Definition: af_stereowiden.c:32
src
#define src
Definition: vp8dsp.c:254
AV_CH_LAYOUT_STEREO
#define AV_CH_LAYOUT_STEREO
Definition: channel_layout.h:86
AVFilterPad
A filter pad used for either input or output.
Definition: internal.h:54
StereoWidenContext
Definition: af_stereowiden.c:28
av_cold
#define av_cold
Definition: attributes.h:84
ff_set_common_formats
int ff_set_common_formats(AVFilterContext *ctx, AVFilterFormats *formats)
A helper for query_formats() which sets all links to the same list of formats.
Definition: formats.c:568
AVFILTER_DEFINE_CLASS
AVFILTER_DEFINE_CLASS(stereowiden)
ff_add_channel_layout
int ff_add_channel_layout(AVFilterChannelLayouts **l, uint64_t channel_layout)
Definition: formats.c:343
s
#define s(width, name)
Definition: cbs_vp9.c:257
outputs
static const AVFilterPad outputs[]
Definition: af_stereowiden.c:150
AVMEDIA_TYPE_AUDIO
@ AVMEDIA_TYPE_AUDIO
Definition: avutil.h:202
StereoWidenContext::buffer
float * buffer
Definition: af_stereowiden.c:36
ctx
AVFormatContext * ctx
Definition: movenc.c:48
filter_frame
static int filter_frame(AVFilterLink *inlink, AVFrame *in)
Definition: af_stereowiden.c:85
if
if(ret)
Definition: filter_design.txt:179
AVClass
Describe the class of an AVClass context structure.
Definition: log.h:67
NULL
#define NULL
Definition: coverity.c:32
av_frame_copy_props
int av_frame_copy_props(AVFrame *dst, const AVFrame *src)
Copy only "metadata" fields from src to dst.
Definition: frame.c:654
StereoWidenContext::drymix
float drymix
Definition: af_stereowiden.c:34
ff_add_format
int ff_add_format(AVFilterFormats **avff, int64_t fmt)
Add fmt to the list of media formats contained in *avff.
Definition: formats.c:337
StereoWidenContext::delay
float delay
Definition: af_stereowiden.c:31
for
for(j=16;j >0;--j)
Definition: h264pred_template.c:469
NULL_IF_CONFIG_SMALL
#define NULL_IF_CONFIG_SMALL(x)
Return NULL if CONFIG_SMALL is true, otherwise the argument without modification.
Definition: internal.h:188
ff_af_stereowiden
AVFilter ff_af_stereowiden
Definition: af_stereowiden.c:158
av_frame_is_writable
int av_frame_is_writable(AVFrame *frame)
Check if the frame data is writable.
Definition: frame.c:594
StereoWidenContext::length
int length
Definition: af_stereowiden.c:38
AV_OPT_TYPE_FLOAT
@ AV_OPT_TYPE_FLOAT
Definition: opt.h:226
layout
Filter the word “frame” indicates either a video frame or a group of audio as stored in an AVFrame structure Format for each input and each output the list of supported formats For video that means pixel format For audio that means channel layout
Definition: filter_design.txt:18
in
uint8_t pi<< 24) CONV_FUNC_GROUP(AV_SAMPLE_FMT_FLT, float, AV_SAMPLE_FMT_U8, uint8_t,(*(const uint8_t *) pi - 0x80) *(1.0f/(1<< 7))) CONV_FUNC_GROUP(AV_SAMPLE_FMT_DBL, double, AV_SAMPLE_FMT_U8, uint8_t,(*(const uint8_t *) pi - 0x80) *(1.0/(1<< 7))) CONV_FUNC_GROUP(AV_SAMPLE_FMT_U8, uint8_t, AV_SAMPLE_FMT_S16, int16_t,(*(const int16_t *) pi >> 8)+0x80) CONV_FUNC_GROUP(AV_SAMPLE_FMT_FLT, float, AV_SAMPLE_FMT_S16, int16_t, *(const int16_t *) pi *(1.0f/(1<< 15))) CONV_FUNC_GROUP(AV_SAMPLE_FMT_DBL, double, AV_SAMPLE_FMT_S16, int16_t, *(const int16_t *) pi *(1.0/(1<< 15))) CONV_FUNC_GROUP(AV_SAMPLE_FMT_U8, uint8_t, AV_SAMPLE_FMT_S32, int32_t,(*(const int32_t *) pi >> 24)+0x80) CONV_FUNC_GROUP(AV_SAMPLE_FMT_FLT, float, AV_SAMPLE_FMT_S32, int32_t, *(const int32_t *) pi *(1.0f/(1U<< 31))) CONV_FUNC_GROUP(AV_SAMPLE_FMT_DBL, double, AV_SAMPLE_FMT_S32, int32_t, *(const int32_t *) pi *(1.0/(1U<< 31))) CONV_FUNC_GROUP(AV_SAMPLE_FMT_U8, uint8_t, AV_SAMPLE_FMT_FLT, float, av_clip_uint8(lrintf(*(const float *) pi *(1<< 7))+0x80)) CONV_FUNC_GROUP(AV_SAMPLE_FMT_S16, int16_t, AV_SAMPLE_FMT_FLT, float, av_clip_int16(lrintf(*(const float *) pi *(1<< 15)))) CONV_FUNC_GROUP(AV_SAMPLE_FMT_S32, int32_t, AV_SAMPLE_FMT_FLT, float, av_clipl_int32(llrintf(*(const float *) pi *(1U<< 31)))) CONV_FUNC_GROUP(AV_SAMPLE_FMT_U8, uint8_t, AV_SAMPLE_FMT_DBL, double, av_clip_uint8(lrint(*(const double *) pi *(1<< 7))+0x80)) CONV_FUNC_GROUP(AV_SAMPLE_FMT_S16, int16_t, AV_SAMPLE_FMT_DBL, double, av_clip_int16(lrint(*(const double *) pi *(1<< 15)))) CONV_FUNC_GROUP(AV_SAMPLE_FMT_S32, int32_t, AV_SAMPLE_FMT_DBL, double, av_clipl_int32(llrint(*(const double *) pi *(1U<< 31)))) #define SET_CONV_FUNC_GROUP(ofmt, ifmt) static void set_generic_function(AudioConvert *ac) { } void ff_audio_convert_free(AudioConvert **ac) { if(! *ac) return;ff_dither_free(&(*ac) ->dc);av_freep(ac);} AudioConvert *ff_audio_convert_alloc(AVAudioResampleContext *avr, enum AVSampleFormat out_fmt, enum AVSampleFormat in_fmt, int channels, int sample_rate, int apply_map) { AudioConvert *ac;int in_planar, out_planar;ac=av_mallocz(sizeof(*ac));if(!ac) return NULL;ac->avr=avr;ac->out_fmt=out_fmt;ac->in_fmt=in_fmt;ac->channels=channels;ac->apply_map=apply_map;if(avr->dither_method !=AV_RESAMPLE_DITHER_NONE &&av_get_packed_sample_fmt(out_fmt)==AV_SAMPLE_FMT_S16 &&av_get_bytes_per_sample(in_fmt) > 2) { ac->dc=ff_dither_alloc(avr, out_fmt, in_fmt, channels, sample_rate, apply_map);if(!ac->dc) { av_free(ac);return NULL;} return ac;} in_planar=ff_sample_fmt_is_planar(in_fmt, channels);out_planar=ff_sample_fmt_is_planar(out_fmt, channels);if(in_planar==out_planar) { ac->func_type=CONV_FUNC_TYPE_FLAT;ac->planes=in_planar ? ac->channels :1;} else if(in_planar) ac->func_type=CONV_FUNC_TYPE_INTERLEAVE;else ac->func_type=CONV_FUNC_TYPE_DEINTERLEAVE;set_generic_function(ac);if(ARCH_AARCH64) ff_audio_convert_init_aarch64(ac);if(ARCH_ARM) ff_audio_convert_init_arm(ac);if(ARCH_X86) ff_audio_convert_init_x86(ac);return ac;} int ff_audio_convert(AudioConvert *ac, AudioData *out, AudioData *in) { int use_generic=1;int len=in->nb_samples;int p;if(ac->dc) { av_log(ac->avr, AV_LOG_TRACE, "%d samples - audio_convert: %s to %s (dithered)\n", len, av_get_sample_fmt_name(ac->in_fmt), av_get_sample_fmt_name(ac->out_fmt));return ff_convert_dither(ac-> in
Definition: audio_convert.c:326
AVFilterPad::name
const char * name
Pad name.
Definition: internal.h:60
AVFilter
Filter definition.
Definition: avfilter.h:144
ret
ret
Definition: filter_design.txt:187
left
Tag MUST be and< 10hcoeff half pel interpolation filter coefficients, hcoeff[0] are the 2 middle coefficients[1] are the next outer ones and so on, resulting in a filter like:...eff[2], hcoeff[1], hcoeff[0], hcoeff[0], hcoeff[1], hcoeff[2] ... the sign of the coefficients is not explicitly stored but alternates after each coeff and coeff[0] is positive, so ...,+,-,+,-,+,+,-,+,-,+,... hcoeff[0] is not explicitly stored but found by subtracting the sum of all stored coefficients with signs from 32 hcoeff[0]=32 - hcoeff[1] - hcoeff[2] - ... a good choice for hcoeff and htaps is htaps=6 hcoeff={40,-10, 2} an alternative which requires more computations at both encoder and decoder side and may or may not be better is htaps=8 hcoeff={42,-14, 6,-2}ref_frames minimum of the number of available reference frames and max_ref_frames for example the first frame after a key frame always has ref_frames=1spatial_decomposition_type wavelet type 0 is a 9/7 symmetric compact integer wavelet 1 is a 5/3 symmetric compact integer wavelet others are reserved stored as delta from last, last is reset to 0 if always_reset||keyframeqlog quality(logarithmic quantizer scale) stored as delta from last, last is reset to 0 if always_reset||keyframemv_scale stored as delta from last, last is reset to 0 if always_reset||keyframe FIXME check that everything works fine if this changes between framesqbias dequantization bias stored as delta from last, last is reset to 0 if always_reset||keyframeblock_max_depth maximum depth of the block tree stored as delta from last, last is reset to 0 if always_reset||keyframequant_table quantization tableHighlevel bitstream structure:==============================--------------------------------------------|Header|--------------------------------------------|------------------------------------|||Block0||||split?||||yes no||||......... intra?||||:Block01 :yes no||||:Block02 :....... ..........||||:Block03 ::y DC ::ref index:||||:Block04 ::cb DC ::motion x :||||......... :cr DC ::motion y :||||....... ..........|||------------------------------------||------------------------------------|||Block1|||...|--------------------------------------------|------------ ------------ ------------|||Y subbands||Cb subbands||Cr subbands||||--- ---||--- ---||--- ---|||||LL0||HL0||||LL0||HL0||||LL0||HL0|||||--- ---||--- ---||--- ---||||--- ---||--- ---||--- ---|||||LH0||HH0||||LH0||HH0||||LH0||HH0|||||--- ---||--- ---||--- ---||||--- ---||--- ---||--- ---|||||HL1||LH1||||HL1||LH1||||HL1||LH1|||||--- ---||--- ---||--- ---||||--- ---||--- ---||--- ---|||||HH1||HL2||||HH1||HL2||||HH1||HL2|||||...||...||...|||------------ ------------ ------------|--------------------------------------------Decoding process:=================------------|||Subbands|------------||||------------|Intra DC||||LL0 subband prediction ------------|\ Dequantization ------------------- \||Reference frames|\ IDWT|------- -------|Motion \|||Frame 0||Frame 1||Compensation . OBMC v -------|------- -------|--------------. \------> Frame n output Frame Frame<----------------------------------/|...|------------------- Range Coder:============Binary Range Coder:------------------- The implemented range coder is an adapted version based upon "Range encoding: an algorithm for removing redundancy from a digitised message." by G. N. N. Martin. The symbols encoded by the Snow range coder are bits(0|1). The associated probabilities are not fix but change depending on the symbol mix seen so far. bit seen|new state ---------+----------------------------------------------- 0|256 - state_transition_table[256 - old_state];1|state_transition_table[old_state];state_transition_table={ 0, 0, 0, 0, 0, 0, 0, 0, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31, 32, 33, 34, 35, 36, 37, 37, 38, 39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 56, 57, 58, 59, 60, 61, 62, 63, 64, 65, 66, 67, 68, 69, 70, 71, 72, 73, 74, 75, 75, 76, 77, 78, 79, 80, 81, 82, 83, 84, 85, 86, 87, 88, 89, 90, 91, 92, 93, 94, 94, 95, 96, 97, 98, 99, 100, 101, 102, 103, 104, 105, 106, 107, 108, 109, 110, 111, 112, 113, 114, 114, 115, 116, 117, 118, 119, 120, 121, 122, 123, 124, 125, 126, 127, 128, 129, 130, 131, 132, 133, 133, 134, 135, 136, 137, 138, 139, 140, 141, 142, 143, 144, 145, 146, 147, 148, 149, 150, 151, 152, 152, 153, 154, 155, 156, 157, 158, 159, 160, 161, 162, 163, 164, 165, 166, 167, 168, 169, 170, 171, 171, 172, 173, 174, 175, 176, 177, 178, 179, 180, 181, 182, 183, 184, 185, 186, 187, 188, 189, 190, 190, 191, 192, 194, 194, 195, 196, 197, 198, 199, 200, 201, 202, 202, 204, 205, 206, 207, 208, 209, 209, 210, 211, 212, 213, 215, 215, 216, 217, 218, 219, 220, 220, 222, 223, 224, 225, 226, 227, 227, 229, 229, 230, 231, 232, 234, 234, 235, 236, 237, 238, 239, 240, 241, 242, 243, 244, 245, 246, 247, 248, 248, 0, 0, 0, 0, 0, 0, 0};FIXME Range Coding of integers:------------------------- FIXME Neighboring Blocks:===================left and top are set to the respective blocks unless they are outside of the image in which case they are set to the Null block top-left is set to the top left block unless it is outside of the image in which case it is set to the left block if this block has no larger parent block or it is at the left side of its parent block and the top right block is not outside of the image then the top right block is used for top-right else the top-left block is used Null block y, cb, cr are 128 level, ref, mx and my are 0 Motion Vector Prediction:=========================1. the motion vectors of all the neighboring blocks are scaled to compensate for the difference of reference frames scaled_mv=(mv *(256 *(current_reference+1)/(mv.reference+1))+128)> the median of the scaled left
Definition: snow.txt:386
ff_all_samplerates
AVFilterFormats * ff_all_samplerates(void)
Definition: formats.c:395
av_calloc
void * av_calloc(size_t nmemb, size_t size)
Non-inlined equivalent of av_mallocz_array().
Definition: mem.c:244
channel_layout.h
avfilter.h
StereoWidenContext::cur
float * cur
Definition: af_stereowiden.c:37
AVFilterContext
An instance of a filter.
Definition: avfilter.h:338
audio.h
query_formats
static int query_formats(AVFilterContext *ctx)
Definition: af_stereowiden.c:54
av_freep
#define av_freep(p)
Definition: tableprint_vlc.h:35
OFFSET
#define OFFSET(x)
Definition: af_stereowiden.c:41
AVFILTER_FLAG_SUPPORT_TIMELINE_INTERNAL
#define AVFILTER_FLAG_SUPPORT_TIMELINE_INTERNAL
Same as AVFILTER_FLAG_SUPPORT_TIMELINE_GENERIC, except that the filter will have its filter_frame() c...
Definition: avfilter.h:133
flags
#define flags(name, subs,...)
Definition: cbs_av1.c:565
ff_set_common_samplerates
int ff_set_common_samplerates(AVFilterContext *ctx, AVFilterFormats *samplerates)
Definition: formats.c:556
AV_SAMPLE_FMT_FLT
@ AV_SAMPLE_FMT_FLT
float
Definition: samplefmt.h:63
StereoWidenContext::crossfeed
float crossfeed
Definition: af_stereowiden.c:33
config_input
static int config_input(AVFilterLink *inlink)
Definition: af_stereowiden.c:70
stereowiden_options
static const AVOption stereowiden_options[]
Definition: af_stereowiden.c:44