49 #define OFFSET(x) offsetof(OWDenoiseContext, x) 50 #define FLAGS AV_OPT_FLAG_FILTERING_PARAM|AV_OPT_FLAG_VIDEO_PARAM 63 { 0, 48, 12, 60, 3, 51, 15, 63 },
64 { 32, 16, 44, 28, 35, 19, 47, 31 },
65 { 8, 56, 4, 52, 11, 59, 7, 55 },
66 { 40, 24, 36, 20, 43, 27, 39, 23 },
67 { 2, 50, 14, 62, 1, 49, 13, 61 },
68 { 34, 18, 46, 30, 33, 17, 45, 29 },
69 { 10, 58, 6, 54, 9, 57, 5, 53 },
70 { 42, 26, 38, 22, 41, 25, 37, 21 },
73 static const double coeff[2][5] = {
104 static inline void decompose(
float *dst_l,
float *dst_h,
const float *
src,
108 for (x = 0; x <
w; x++) {
110 double sum_h = src[x *
linesize] * coeff[1][0];
111 for (i = 1; i <= 4; i++) {
115 sum_l += coeff[0][
i] *
s;
116 sum_h += coeff[1][
i] *
s;
123 static inline void compose(
float *dst,
const float *src_l,
const float *src_h,
127 for (x = 0; x <
w; x++) {
129 double sum_h = src_h[x *
linesize] * icoeff[1][0];
130 for (i = 1; i <= 4; i++) {
134 sum_l += icoeff[0][
i] * (src_l[x0] + src_l[x1]);
135 sum_h += icoeff[1][
i] * (src_h[x0] + src_h[x1]);
137 dst[x *
linesize] = (sum_l + sum_h) * 0.5;
142 int xlinesize,
int ylinesize,
146 for (y = 0; y <
h; y++)
147 for (x = 0; x <
step; x++)
148 decompose(dst_l + ylinesize*y + xlinesize*x,
149 dst_h + ylinesize*y + xlinesize*x,
150 src + ylinesize*y + xlinesize*x,
151 step * xlinesize, (w - x + step - 1) / step);
154 static inline void compose2D(
float *dst,
const float *src_l,
const float *src_h,
155 int xlinesize,
int ylinesize,
159 for (y = 0; y <
h; y++)
160 for (x = 0; x <
step; x++)
161 compose(dst + ylinesize*y + xlinesize*x,
162 src_l + ylinesize*y + xlinesize*x,
163 src_h + ylinesize*y + xlinesize*x,
164 step * xlinesize, (w - x + step - 1) / step);
170 decompose2D(temp[0], temp[1], src, 1, linesize, step, w, h);
171 decompose2D( dst[0], dst[1], temp[0], linesize, 1, step, h, w);
172 decompose2D( dst[2], dst[3], temp[1], linesize, 1, step, h, w);
178 compose2D(temp[0], src[0], src[1], linesize, 1, step, h, w);
179 compose2D(temp[1], src[2], src[3], linesize, 1, step, h, w);
180 compose2D(dst, temp[0], temp[1], 1, linesize, step, w, h);
184 uint8_t *dst,
int dst_linesize,
190 while (1<<depth > width || 1<<depth > height)
194 for (y = 0; y <
height; y++)
195 for(x = 0; x <
width; x++)
198 const uint16_t *src16 = (
const uint16_t *)src;
201 for (y = 0; y <
height; y++)
202 for(x = 0; x <
width; x++)
203 s->
plane[0][0][y*s->
linesize + x] = src16[y*src_linesize + x];
206 for (i = 0; i <
depth; i++)
209 for (i = 0; i <
depth; i++) {
210 for (j = 1; j < 4; j++) {
211 for (y = 0; y <
height; y++) {
212 for (x = 0; x <
width; x++) {
214 if (v > strength) v -= strength;
215 else if (v < -strength) v += strength;
222 for (i = depth-1; i >= 0; i--)
226 for (y = 0; y <
height; y++) {
227 for (x = 0; x <
width; x++) {
229 if ((
unsigned)i > 255
U) i = ~(i >> 31);
230 dst[y*dst_linesize + x] =
i;
234 uint16_t *dst16 = (uint16_t *)dst;
237 for (y = 0; y <
height; y++) {
238 for (x = 0; x <
width; x++) {
240 dst16[y*dst_linesize + x] =
i;
288 inlink->
w, inlink->
h);
330 for (j = 0; j < 4; j++) {
331 for (i = 0; i <= s->
depth; i++) {
345 for (j = 0; j < 4; j++)
346 for (i = 0; i <= s->
depth; i++)
374 .
inputs = owdenoise_inputs,
376 .priv_class = &owdenoise_class,
static void compose(float *dst, const float *src_l, const float *src_h, int linesize, int w)
#define AV_PIX_FMT_YUV440P10
const AVPixFmtDescriptor * av_pix_fmt_desc_get(enum AVPixelFormat pix_fmt)
This structure describes decoded (raw) audio or video data.
#define AV_PIX_FMT_YUV444P14
planar YUV 4:4:4, 24bpp, (1 Cr & Cb sample per 1x1 Y samples)
Main libavfilter public API header.
static int config_input(AVFilterLink *inlink)
int h
agreed upon image height
static void decompose2D2(float *dst[4], float *src, float *temp[2], int linesize, int step, int w, int h)
#define AV_PIX_FMT_YUV420P12
static void filter(OWDenoiseContext *s, uint8_t *dst, int dst_linesize, const uint8_t *src, int src_linesize, int width, int height, double strength)
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.
#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.
planar YUV 4:2:0, 20bpp, (1 Cr & Cb sample per 2x2 Y & A samples)
AVComponentDescriptor comp[4]
Parameters that describe how pixels are packed.
static void decompose(float *dst_l, float *dst_h, const float *src, int linesize, int w)
static const AVOption owdenoise_options[]
#define DECLARE_ALIGNED(n, t, v)
Declare a variable that is aligned in memory.
static void decompose2D(float *dst_l, float *dst_h, const float *src, int xlinesize, int ylinesize, int step, int w, int h)
#define AV_PIX_FMT_YUV444P16
#define AV_PIX_FMT_YUV422P12
A filter pad used for either input or output.
A link between two filters.
planar YUV 4:2:2 24bpp, (1 Cr & Cb sample per 2x1 Y & A samples)
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.
#define NULL_IF_CONFIG_SMALL(x)
Return NULL if CONFIG_SMALL is true, otherwise the argument without modification. ...
static int filter_frame(AVFilterLink *inlink, AVFrame *in)
void * priv
private data for use by the filter
#define AV_PIX_FMT_YUV444P10
planar YUV 4:2:2, 16bpp, (1 Cr & Cb sample per 2x1 Y samples)
int w
agreed upon image width
#define AV_PIX_FMT_YUV422P9
static void compose2D2(float *dst, float *src[4], float *temp[2], int linesize, int step, int w, int h)
static av_always_inline av_const int avpriv_mirror(int x, int w)
#define AV_PIX_FMT_YUV444P9
static const AVFilterPad outputs[]
int format
agreed upon media format
static const AVFilterPad owdenoise_outputs[]
#define AV_PIX_FMT_YUV420P16
#define AV_PIX_FMT_YUV420P14
AVFILTER_DEFINE_CLASS(owdenoise)
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.
planar YUV 4:4:4 32bpp, (1 Cr & Cb sample per 1x1 Y & A samples)
Descriptor that unambiguously describes how the bits of a pixel are stored in the up to 4 data planes...
static const uint8_t dither[8][8]
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
#define AV_PIX_FMT_YUV420P10
planar YUV 4:1:0, 9bpp, (1 Cr & Cb sample per 4x4 Y samples)
Describe the class of an AVClass context structure.
static const double icoeff[2][5]
const char * name
Filter name.
static int query_formats(AVFilterContext *ctx)
#define AV_PIX_FMT_YUV440P12
static void compose2D(float *dst, const float *src_l, const float *src_h, int xlinesize, int ylinesize, int step, int w, int h)
#define AV_PIX_FMT_YUV420P9
AVFilterLink ** outputs
array of pointers to output links
static enum AVPixelFormat pix_fmts[]
#define AV_PIX_FMT_YUV422P14
#define flags(name, subs,...)
#define AV_PIX_FMT_YUV422P10
#define AV_PIX_FMT_YUV444P12
uint8_t * data[AV_NUM_DATA_POINTERS]
pointer to the picture/channel planes.
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)
static av_cold void uninit(AVFilterContext *ctx)
planar YUV 4:1:1, 12bpp, (1 Cr & Cb sample per 4x1 Y samples)
AVFilterContext * dst
dest filter
static const double coeff[2][5]
planar YUV 4:4:0 (1 Cr & Cb sample per 1x2 Y samples)
#define av_malloc_array(a, b)
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
int depth
Number of bits in the component.
AVPixelFormat
Pixel format.
#define AV_PIX_FMT_YUV422P16
static const AVFilterPad owdenoise_inputs[]
int av_frame_copy_props(AVFrame *dst, const AVFrame *src)
Copy only "metadata" fields from src to dst.
trying all byte sequences megabyte in length and selecting the best looking sequence will yield cases to try But a word about which is also called distortion Distortion can be quantified by almost any quality measurement one chooses the sum of squared differences is used but more complex methods that consider psychovisual effects can be used as well It makes no difference in this discussion First step
#define AV_CEIL_RSHIFT(a, b)