48 {0x00,0x60,0x18,0x78,0x06,0x66,0x1E,0x7E},
49 {0x40,0x20,0x58,0x38,0x46,0x26,0x5E,0x3E},
50 {0x10,0x70,0x08,0x68,0x16,0x76,0x0E,0x6E},
51 {0x50,0x30,0x48,0x28,0x56,0x36,0x4E,0x2E},
52 {0x04,0x64,0x1C,0x7C,0x02,0x62,0x1A,0x7A},
53 {0x44,0x24,0x5C,0x3C,0x42,0x22,0x5A,0x3A},
54 {0x14,0x74,0x0C,0x6C,0x12,0x72,0x0A,0x6A},
55 {0x54,0x34,0x4C,0x2C,0x52,0x32,0x4A,0x2A},
61 for (x = 0; x <
width; dc += x & 1, x++) {
62 int pix = src[x] << 7;
63 int delta = dc[0] - pix;
64 int m =
abs(delta) * thresh >> 16;
65 m =
FFMAX(0, 127 - m);
66 m = m * m * delta >> 14;
67 pix += m + dithers[x & 7];
75 for (x = 0; x <
width; x++) {
76 v = buf1[x] + src[2 * x] + src[2 * x + 1] + src[2 * x + src_linesize] + src[2 * x + 1 + src_linesize];
85 int bstride =
FFALIGN(width, 16) / 2;
87 uint32_t dc_factor = (1 << 21) / (r * r);
88 uint16_t *
dc = ctx->
buf + 16;
89 uint16_t *buf = ctx->
buf + bstride + 32;
92 memset(dc, 0, (bstride + 16) *
sizeof(*buf));
93 for (y = 0; y <
r; y++)
94 ctx->
blur_line(dc, buf + y * bstride, buf + (y - 1) * bstride, src + 2 * y * src_linesize, src_linesize, width / 2);
97 int mod = ((y +
r) / 2) %
r;
98 uint16_t *buf0 = buf + mod * bstride;
99 uint16_t *buf1 = buf + (mod ? mod - 1 : r - 1) * bstride;
101 ctx->
blur_line(dc, buf0, buf1, src + (y + r) * src_linesize, src_linesize, width / 2);
102 for (x = v = 0; x <
r; x++)
104 for (; x < width / 2; x++) {
105 v += dc[x] - dc[x-
r];
106 dc[x-
r] = v * dc_factor >> 16;
108 for (; x < (width + r + 1) / 2; x++)
109 dc[x-r] = v * dc_factor >> 16;
110 for (x = -r / 2; x < 0; x++)
114 for (y = 0; y <
r; y++)
115 ctx->
filter_line(dst + y * dst_linesize, src + y * src_linesize, dc - r / 2, width, thresh,
dither[y & 7]);
117 ctx->
filter_line(dst + y * dst_linesize, src + y * src_linesize, dc - r / 2, width, thresh,
dither[y & 7]);
118 if (++y >= height)
break;
119 ctx->
filter_line(dst + y * dst_linesize, src + y * src_linesize, dc - r / 2, width, thresh,
dither[y & 7]);
120 if (++y >= height)
break;
204 for (p = 0; p < 4 && in->
data[p] && in->
linesize[p]; p++) {
214 if (
FFMIN(w, h) > 2 * r)
216 else if (out->
data[p] != in->
data[p])
226 #define OFFSET(x) offsetof(GradFunContext, x) 227 #define FLAGS AV_OPT_FLAG_VIDEO_PARAM|AV_OPT_FLAG_FILTERING_PARAM 230 {
"strength",
"The maximum amount by which the filter will change any one pixel.",
OFFSET(strength),
AV_OPT_TYPE_FLOAT, { .dbl = 1.2 }, 0.51, 64,
FLAGS },
259 .priv_class = &gradfun_class,
263 .
inputs = avfilter_vf_gradfun_inputs,
264 .
outputs = avfilter_vf_gradfun_outputs,
const AVPixFmtDescriptor * av_pix_fmt_desc_get(enum AVPixelFormat pix_fmt)
This structure describes decoded (raw) audio or video data.
planar YUV 4:4:4, 24bpp, (1 Cr & Cb sample per 1x1 Y samples)
Main libavfilter public API header.
int h
agreed upon image height
Holds instance-specific information for gradfun.
AVFrame * ff_get_video_buffer(AVFilterLink *link, int w, int h)
Request a picture buffer with a specific set of permissions.
uint8_t log2_chroma_w
Amount to shift the luma width right to find the chroma width.
void * av_calloc(size_t nmemb, size_t size)
Non-inlined equivalent of av_mallocz_array().
#define AVFILTER_FLAG_SUPPORT_TIMELINE_GENERIC
Some filters support a generic "enable" expression option that can be used to enable or disable a fil...
const char * name
Pad name.
int ff_filter_frame(AVFilterLink *link, AVFrame *frame)
Send a frame of data to the next filter.
int chroma_h
weight of the chroma planes
static int filter_frame(AVFilterLink *inlink, AVFrame *in)
#define DECLARE_ALIGNED(n, t, v)
Declare a variable that is aligned in memory.
static int config_input(AVFilterLink *inlink)
#define AV_LOG_VERBOSE
Detailed information.
static const AVFilterPad avfilter_vf_gradfun_outputs[]
A filter pad used for either input or output.
A link between two filters.
static av_cold void uninit(AVFilterContext *ctx)
uint8_t log2_chroma_h
Amount to shift the luma height right to find the chroma height.
void av_frame_free(AVFrame **frame)
Free the frame and any dynamically allocated objects in it, e.g.
static void filter(GradFunContext *ctx, uint8_t *dst, const uint8_t *src, int width, int height, int dst_linesize, int src_linesize, int r)
#define NULL_IF_CONFIG_SMALL(x)
Return NULL if CONFIG_SMALL is true, otherwise the argument without modification. ...
void * priv
private data for use by the filter
static void direct(const float *in, const FFTComplex *ir, int len, float *out)
static const uint8_t dithers[8][8][8]
planar YUV 4:2:2, 16bpp, (1 Cr & Cb sample per 2x1 Y samples)
int w
agreed upon image width
void ff_gradfun_filter_line_c(uint8_t *dst, const uint8_t *src, const uint16_t *dc, int width, int thresh, const uint16_t *dithers)
void ff_gradfun_init_x86(GradFunContext *gf)
static const AVFilterPad outputs[]
int format
agreed upon media format
uint16_t * buf
holds image data for blur algorithm passed into filter.
static const uint16_t dither[8][8]
int av_frame_is_writable(AVFrame *frame)
Check if the frame data is writable.
int linesize[AV_NUM_DATA_POINTERS]
For video, size in bytes of each picture line.
Descriptor that unambiguously describes how the bits of a pixel are stored in the up to 4 data planes...
static int mod(int a, int b)
Modulo operation with only positive remainders.
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 top and top right vectors is used as motion vector prediction the used motion vector is the sum of the predictor and(mvx_diff, mvy_diff)*mv_scale Intra DC Prediction block[y][x] dc[1]
static av_cold int init(AVFilterContext *ctx)
these buffered frames must be flushed immediately if a new input produces new the filter must not call request_frame to get more It must just process the frame or queue it The task of requesting more frames is left to the filter s request_frame method or the application If a filter has several inputs
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
planar YUV 4:1:0, 9bpp, (1 Cr & Cb sample per 4x4 Y samples)
const char * name
Filter name.
void(* filter_line)(uint8_t *dst, const uint8_t *src, const uint16_t *dc, int width, int thresh, const uint16_t *dithers)
DSP functions.
static const AVFilterPad avfilter_vf_gradfun_inputs[]
AVFilterLink ** outputs
array of pointers to output links
static enum AVPixelFormat pix_fmts[]
#define flags(name, subs,...)
uint8_t * data[AV_NUM_DATA_POINTERS]
pointer to the picture/channel planes.
static int query_formats(AVFilterContext *ctx)
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
planar YUV 4:2:0, 12bpp, (1 Cr & Cb sample per 2x2 Y samples)
int chroma_w
width of the chroma planes
common internal and external API header
void(* blur_line)(uint16_t *dc, uint16_t *buf, const uint16_t *buf1, const uint8_t *src, int src_linesize, int width)
planar YUV 4:1:1, 12bpp, (1 Cr & Cb sample per 4x1 Y samples)
AVFilterContext * dst
dest filter
int thresh
threshold for gradient algorithm
int chroma_r
blur radius for the chroma planes
AVFILTER_DEFINE_CLASS(gradfun)
void ff_gradfun_blur_line_c(uint16_t *dc, uint16_t *buf, const uint16_t *buf1, const uint8_t *src, int src_linesize, int width)
planar YUV 4:4:0 (1 Cr & Cb sample per 1x2 Y samples)
void av_image_copy_plane(uint8_t *dst, int dst_linesize, const uint8_t *src, int src_linesize, int bytewidth, int height)
Copy image plane from src to dst.
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
AVPixelFormat
Pixel format.
int av_frame_copy_props(AVFrame *dst, const AVFrame *src)
Copy only "metadata" fields from src to dst.
static const AVOption gradfun_options[]
#define AV_CEIL_RSHIFT(a, b)