1 /*
2 * Copyright (C) 2016 Open Broadcast Systems Ltd.
3 * Author 2016 Rostislav Pehlivanov <atomnuker@gmail.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
22 #include "libavutil/pixdesc.h"
23 #include "libavutil/opt.h"
24 #include "libavutil/version.h"
25 #include "codec_internal.h"
26 #include "dirac.h"
27 #include "encode.h"
28 #include "put_bits.h"
29 #include "version.h"
30
31 #include "vc2enc_dwt.h"
32 #include "diractab.h"
33
34 /* The limited size resolution of each slice forces us to do this */
35 #define SSIZE_ROUND(b) (FFALIGN((b), s->size_scaler) + 4 + s->prefix_bytes)
36
37 /* Decides the cutoff point in # of slices to distribute the leftover bytes */
38 #define SLICE_REDIST_TOTAL 150
39
40 typedef struct VC2BaseVideoFormat {
41 enum AVPixelFormat pix_fmt;
42 AVRational time_base;
43 int width, height, interlaced, level;
44 const char *name;
45 } VC2BaseVideoFormat;
46
47 static const VC2BaseVideoFormat base_video_fmts[] = {
48 { 0 }, /* Custom format, here just to make indexing equal to base_vf */
49 { AV_PIX_FMT_YUV420P, { 1001, 15000 }, 176, 120, 0, 1, "QSIF525" },
50 { AV_PIX_FMT_YUV420P, { 2, 25 }, 176, 144, 0, 1, "QCIF" },
51 { AV_PIX_FMT_YUV420P, { 1001, 15000 }, 352, 240, 0, 1, "SIF525" },
52 { AV_PIX_FMT_YUV420P, { 2, 25 }, 352, 288, 0, 1, "CIF" },
53 { AV_PIX_FMT_YUV420P, { 1001, 15000 }, 704, 480, 0, 1, "4SIF525" },
54 { AV_PIX_FMT_YUV420P, { 2, 25 }, 704, 576, 0, 1, "4CIF" },
55
56 { AV_PIX_FMT_YUV422P10, { 1001, 30000 }, 720, 480, 1, 2, "SD480I-60" },
57 { AV_PIX_FMT_YUV422P10, { 1, 25 }, 720, 576, 1, 2, "SD576I-50" },
58
59 { AV_PIX_FMT_YUV422P10, { 1001, 60000 }, 1280, 720, 0, 3, "HD720P-60" },
60 { AV_PIX_FMT_YUV422P10, { 1, 50 }, 1280, 720, 0, 3, "HD720P-50" },
61 { AV_PIX_FMT_YUV422P10, { 1001, 30000 }, 1920, 1080, 1, 3, "HD1080I-60" },
62 { AV_PIX_FMT_YUV422P10, { 1, 25 }, 1920, 1080, 1, 3, "HD1080I-50" },
63 { AV_PIX_FMT_YUV422P10, { 1001, 60000 }, 1920, 1080, 0, 3, "HD1080P-60" },
64 { AV_PIX_FMT_YUV422P10, { 1, 50 }, 1920, 1080, 0, 3, "HD1080P-50" },
65
66 { AV_PIX_FMT_YUV444P12, { 1, 24 }, 2048, 1080, 0, 4, "DC2K" },
67 { AV_PIX_FMT_YUV444P12, { 1, 24 }, 4096, 2160, 0, 5, "DC4K" },
68
69 { AV_PIX_FMT_YUV422P10, { 1001, 60000 }, 3840, 2160, 0, 6, "UHDTV 4K-60" },
70 { AV_PIX_FMT_YUV422P10, { 1, 50 }, 3840, 2160, 0, 6, "UHDTV 4K-50" },
71
72 { AV_PIX_FMT_YUV422P10, { 1001, 60000 }, 7680, 4320, 0, 7, "UHDTV 8K-60" },
73 { AV_PIX_FMT_YUV422P10, { 1, 50 }, 7680, 4320, 0, 7, "UHDTV 8K-50" },
74
75 { AV_PIX_FMT_YUV422P10, { 1001, 24000 }, 1920, 1080, 0, 3, "HD1080P-24" },
76 { AV_PIX_FMT_YUV422P10, { 1001, 30000 }, 720, 486, 1, 2, "SD Pro486" },
77 };
78 static const int base_video_fmts_len = FF_ARRAY_ELEMS(base_video_fmts);
79
80 enum VC2_QM {
81 VC2_QM_DEF = 0,
82 VC2_QM_COL,
83 VC2_QM_FLAT,
84
85 VC2_QM_NB
86 };
87
88 typedef struct SubBand {
89 dwtcoef *buf;
90 ptrdiff_t stride;
91 int width;
92 int height;
93 } SubBand;
94
95 typedef struct Plane {
96 SubBand band[MAX_DWT_LEVELS][4];
97 dwtcoef *coef_buf;
98 int width;
99 int height;
100 int dwt_width;
101 int dwt_height;
102 ptrdiff_t coef_stride;
103 } Plane;
104
105 typedef struct SliceArgs {
106 PutBitContext pb;
107 int cache[DIRAC_MAX_QUANT_INDEX];
108 void *ctx;
109 int x;
110 int y;
111 int quant_idx;
112 int bits_ceil;
113 int bits_floor;
114 int bytes;
115 } SliceArgs;
116
117 typedef struct TransformArgs {
118 void *ctx;
119 Plane *plane;
120 void *idata;
121 ptrdiff_t istride;
122 int field;
123 VC2TransformContext t;
124 } TransformArgs;
125
126 typedef struct VC2EncContext {
127 AVClass *av_class;
128 PutBitContext pb;
129 Plane plane[3];
130 AVCodecContext *avctx;
131 DiracVersionInfo ver;
132
133 SliceArgs *slice_args;
134 TransformArgs transform_args[3];
135
136 /* For conversion from unsigned pixel values to signed */
137 int diff_offset;
138 int bpp;
139 int bpp_idx;
140
141 /* Picture number */
142 uint32_t picture_number;
143
144 /* Base video format */
145 int base_vf;
146 int level;
147 int profile;
148
149 /* Quantization matrix */
150 uint8_t quant[MAX_DWT_LEVELS][4];
151 int custom_quant_matrix;
152
153 /* Division LUT */
154 uint32_t qmagic_lut[116][2];
155
156 int num_x; /* #slices horizontally */
157 int num_y; /* #slices vertically */
158 int prefix_bytes;
159 int size_scaler;
160 int chroma_x_shift;
161 int chroma_y_shift;
162
163 /* Rate control stuff */
164 int frame_max_bytes;
165 int slice_max_bytes;
166 int slice_min_bytes;
167 int q_ceil;
168 int q_avg;
169
170 /* Options */
171 double tolerance;
172 int wavelet_idx;
173 int wavelet_depth;
174 int strict_compliance;
175 int slice_height;
176 int slice_width;
177 int interlaced;
178 enum VC2_QM quant_matrix;
179
180 /* Parse code state */
181 uint32_t next_parse_offset;
182 enum DiracParseCodes last_parse_code;
183 } VC2EncContext;
184
put_vc2_ue_uint(PutBitContext *pb, uint32_t val)185 static av_always_inline void put_vc2_ue_uint(PutBitContext *pb, uint32_t val)
186 {
187 int i;
188 int pbits = 0, bits = 0, topbit = 1, maxval = 1;
189
190 if (!val++) {
191 put_bits(pb, 1, 1);
192 return;
193 }
194
195 while (val > maxval) {
196 topbit <<= 1;
197 maxval <<= 1;
198 maxval |= 1;
199 }
200
201 bits = ff_log2(topbit);
202
203 for (i = 0; i < bits; i++) {
204 topbit >>= 1;
205 pbits <<= 2;
206 if (val & topbit)
207 pbits |= 0x1;
208 }
209
210 put_bits(pb, bits*2 + 1, (pbits << 1) | 1);
211 }
212
count_vc2_ue_uint(uint32_t val)213 static av_always_inline int count_vc2_ue_uint(uint32_t val)
214 {
215 int topbit = 1, maxval = 1;
216
217 if (!val++)
218 return 1;
219
220 while (val > maxval) {
221 topbit <<= 1;
222 maxval <<= 1;
223 maxval |= 1;
224 }
225
226 return ff_log2(topbit)*2 + 1;
227 }
228
229 /* VC-2 10.4 - parse_info() */
encode_parse_info(VC2EncContext *s, enum DiracParseCodes pcode)230 static void encode_parse_info(VC2EncContext *s, enum DiracParseCodes pcode)
231 {
232 uint32_t cur_pos, dist;
233
234 align_put_bits(&s->pb);
235
236 cur_pos = put_bits_count(&s->pb) >> 3;
237
238 /* Magic string */
239 ff_put_string(&s->pb, "BBCD", 0);
240
241 /* Parse code */
242 put_bits(&s->pb, 8, pcode);
243
244 /* Next parse offset */
245 dist = cur_pos - s->next_parse_offset;
246 AV_WB32(s->pb.buf + s->next_parse_offset + 5, dist);
247 s->next_parse_offset = cur_pos;
248 put_bits32(&s->pb, pcode == DIRAC_PCODE_END_SEQ ? 13 : 0);
249
250 /* Last parse offset */
251 put_bits32(&s->pb, s->last_parse_code == DIRAC_PCODE_END_SEQ ? 13 : dist);
252
253 s->last_parse_code = pcode;
254 }
255
256 /* VC-2 11.1 - parse_parameters()
257 * The level dictates what the decoder should expect in terms of resolution
258 * and allows it to quickly reject whatever it can't support. Remember,
259 * this codec kinda targets cheapo FPGAs without much memory. Unfortunately
260 * it also limits us greatly in our choice of formats, hence the flag to disable
261 * strict_compliance */
encode_parse_params(VC2EncContext *s)262 static void encode_parse_params(VC2EncContext *s)
263 {
264 put_vc2_ue_uint(&s->pb, s->ver.major); /* VC-2 demands this to be 2 */
265 put_vc2_ue_uint(&s->pb, s->ver.minor); /* ^^ and this to be 0 */
266 put_vc2_ue_uint(&s->pb, s->profile); /* 3 to signal HQ profile */
267 put_vc2_ue_uint(&s->pb, s->level); /* 3 - 1080/720, 6 - 4K */
268 }
269
270 /* VC-2 11.3 - frame_size() */
encode_frame_size(VC2EncContext *s)271 static void encode_frame_size(VC2EncContext *s)
272 {
273 put_bits(&s->pb, 1, !s->strict_compliance);
274 if (!s->strict_compliance) {
275 AVCodecContext *avctx = s->avctx;
276 put_vc2_ue_uint(&s->pb, avctx->width);
277 put_vc2_ue_uint(&s->pb, avctx->height);
278 }
279 }
280
281 /* VC-2 11.3.3 - color_diff_sampling_format() */
encode_sample_fmt(VC2EncContext *s)282 static void encode_sample_fmt(VC2EncContext *s)
283 {
284 put_bits(&s->pb, 1, !s->strict_compliance);
285 if (!s->strict_compliance) {
286 int idx;
287 if (s->chroma_x_shift == 1 && s->chroma_y_shift == 0)
288 idx = 1; /* 422 */
289 else if (s->chroma_x_shift == 1 && s->chroma_y_shift == 1)
290 idx = 2; /* 420 */
291 else
292 idx = 0; /* 444 */
293 put_vc2_ue_uint(&s->pb, idx);
294 }
295 }
296
297 /* VC-2 11.3.4 - scan_format() */
encode_scan_format(VC2EncContext *s)298 static void encode_scan_format(VC2EncContext *s)
299 {
300 put_bits(&s->pb, 1, !s->strict_compliance);
301 if (!s->strict_compliance)
302 put_vc2_ue_uint(&s->pb, s->interlaced);
303 }
304
305 /* VC-2 11.3.5 - frame_rate() */
encode_frame_rate(VC2EncContext *s)306 static void encode_frame_rate(VC2EncContext *s)
307 {
308 put_bits(&s->pb, 1, !s->strict_compliance);
309 if (!s->strict_compliance) {
310 AVCodecContext *avctx = s->avctx;
311 put_vc2_ue_uint(&s->pb, 0);
312 put_vc2_ue_uint(&s->pb, avctx->time_base.den);
313 put_vc2_ue_uint(&s->pb, avctx->time_base.num);
314 }
315 }
316
317 /* VC-2 11.3.6 - aspect_ratio() */
encode_aspect_ratio(VC2EncContext *s)318 static void encode_aspect_ratio(VC2EncContext *s)
319 {
320 put_bits(&s->pb, 1, !s->strict_compliance);
321 if (!s->strict_compliance) {
322 AVCodecContext *avctx = s->avctx;
323 put_vc2_ue_uint(&s->pb, 0);
324 put_vc2_ue_uint(&s->pb, avctx->sample_aspect_ratio.num);
325 put_vc2_ue_uint(&s->pb, avctx->sample_aspect_ratio.den);
326 }
327 }
328
329 /* VC-2 11.3.7 - clean_area() */
encode_clean_area(VC2EncContext *s)330 static void encode_clean_area(VC2EncContext *s)
331 {
332 put_bits(&s->pb, 1, 0);
333 }
334
335 /* VC-2 11.3.8 - signal_range() */
encode_signal_range(VC2EncContext *s)336 static void encode_signal_range(VC2EncContext *s)
337 {
338 put_bits(&s->pb, 1, !s->strict_compliance);
339 if (!s->strict_compliance)
340 put_vc2_ue_uint(&s->pb, s->bpp_idx);
341 }
342
343 /* VC-2 11.3.9 - color_spec() */
encode_color_spec(VC2EncContext *s)344 static void encode_color_spec(VC2EncContext *s)
345 {
346 AVCodecContext *avctx = s->avctx;
347 put_bits(&s->pb, 1, !s->strict_compliance);
348 if (!s->strict_compliance) {
349 int val;
350 put_vc2_ue_uint(&s->pb, 0);
351
352 /* primaries */
353 put_bits(&s->pb, 1, 1);
354 if (avctx->color_primaries == AVCOL_PRI_BT470BG)
355 val = 2;
356 else if (avctx->color_primaries == AVCOL_PRI_SMPTE170M)
357 val = 1;
358 else if (avctx->color_primaries == AVCOL_PRI_SMPTE240M)
359 val = 1;
360 else
361 val = 0;
362 put_vc2_ue_uint(&s->pb, val);
363
364 /* color matrix */
365 put_bits(&s->pb, 1, 1);
366 if (avctx->colorspace == AVCOL_SPC_RGB)
367 val = 3;
368 else if (avctx->colorspace == AVCOL_SPC_YCOCG)
369 val = 2;
370 else if (avctx->colorspace == AVCOL_SPC_BT470BG)
371 val = 1;
372 else
373 val = 0;
374 put_vc2_ue_uint(&s->pb, val);
375
376 /* transfer function */
377 put_bits(&s->pb, 1, 1);
378 if (avctx->color_trc == AVCOL_TRC_LINEAR)
379 val = 2;
380 else if (avctx->color_trc == AVCOL_TRC_BT1361_ECG)
381 val = 1;
382 else
383 val = 0;
384 put_vc2_ue_uint(&s->pb, val);
385 }
386 }
387
388 /* VC-2 11.3 - source_parameters() */
encode_source_params(VC2EncContext *s)389 static void encode_source_params(VC2EncContext *s)
390 {
391 encode_frame_size(s);
392 encode_sample_fmt(s);
393 encode_scan_format(s);
394 encode_frame_rate(s);
395 encode_aspect_ratio(s);
396 encode_clean_area(s);
397 encode_signal_range(s);
398 encode_color_spec(s);
399 }
400
401 /* VC-2 11 - sequence_header() */
encode_seq_header(VC2EncContext *s)402 static void encode_seq_header(VC2EncContext *s)
403 {
404 align_put_bits(&s->pb);
405 encode_parse_params(s);
406 put_vc2_ue_uint(&s->pb, s->base_vf);
407 encode_source_params(s);
408 put_vc2_ue_uint(&s->pb, s->interlaced); /* Frames or fields coding */
409 }
410
411 /* VC-2 12.1 - picture_header() */
encode_picture_header(VC2EncContext *s)412 static void encode_picture_header(VC2EncContext *s)
413 {
414 align_put_bits(&s->pb);
415 put_bits32(&s->pb, s->picture_number++);
416 }
417
418 /* VC-2 12.3.4.1 - slice_parameters() */
encode_slice_params(VC2EncContext *s)419 static void encode_slice_params(VC2EncContext *s)
420 {
421 put_vc2_ue_uint(&s->pb, s->num_x);
422 put_vc2_ue_uint(&s->pb, s->num_y);
423 put_vc2_ue_uint(&s->pb, s->prefix_bytes);
424 put_vc2_ue_uint(&s->pb, s->size_scaler);
425 }
426
427 /* 1st idx = LL, second - vertical, third - horizontal, fourth - total */
428 static const uint8_t vc2_qm_col_tab[][4] = {
429 {20, 9, 15, 4},
430 { 0, 6, 6, 4},
431 { 0, 3, 3, 5},
432 { 0, 3, 5, 1},
433 { 0, 11, 10, 11}
434 };
435
436 static const uint8_t vc2_qm_flat_tab[][4] = {
437 { 0, 0, 0, 0},
438 { 0, 0, 0, 0},
439 { 0, 0, 0, 0},
440 { 0, 0, 0, 0},
441 { 0, 0, 0, 0}
442 };
443
init_quant_matrix(VC2EncContext *s)444 static void init_quant_matrix(VC2EncContext *s)
445 {
446 int level, orientation;
447
448 if (s->wavelet_depth <= 4 && s->quant_matrix == VC2_QM_DEF) {
449 s->custom_quant_matrix = 0;
450 for (level = 0; level < s->wavelet_depth; level++) {
451 s->quant[level][0] = ff_dirac_default_qmat[s->wavelet_idx][level][0];
452 s->quant[level][1] = ff_dirac_default_qmat[s->wavelet_idx][level][1];
453 s->quant[level][2] = ff_dirac_default_qmat[s->wavelet_idx][level][2];
454 s->quant[level][3] = ff_dirac_default_qmat[s->wavelet_idx][level][3];
455 }
456 return;
457 }
458
459 s->custom_quant_matrix = 1;
460
461 if (s->quant_matrix == VC2_QM_DEF) {
462 for (level = 0; level < s->wavelet_depth; level++) {
463 for (orientation = 0; orientation < 4; orientation++) {
464 if (level <= 3)
465 s->quant[level][orientation] = ff_dirac_default_qmat[s->wavelet_idx][level][orientation];
466 else
467 s->quant[level][orientation] = vc2_qm_col_tab[level][orientation];
468 }
469 }
470 } else if (s->quant_matrix == VC2_QM_COL) {
471 for (level = 0; level < s->wavelet_depth; level++) {
472 for (orientation = 0; orientation < 4; orientation++) {
473 s->quant[level][orientation] = vc2_qm_col_tab[level][orientation];
474 }
475 }
476 } else {
477 for (level = 0; level < s->wavelet_depth; level++) {
478 for (orientation = 0; orientation < 4; orientation++) {
479 s->quant[level][orientation] = vc2_qm_flat_tab[level][orientation];
480 }
481 }
482 }
483 }
484
485 /* VC-2 12.3.4.2 - quant_matrix() */
encode_quant_matrix(VC2EncContext *s)486 static void encode_quant_matrix(VC2EncContext *s)
487 {
488 int level;
489 put_bits(&s->pb, 1, s->custom_quant_matrix);
490 if (s->custom_quant_matrix) {
491 put_vc2_ue_uint(&s->pb, s->quant[0][0]);
492 for (level = 0; level < s->wavelet_depth; level++) {
493 put_vc2_ue_uint(&s->pb, s->quant[level][1]);
494 put_vc2_ue_uint(&s->pb, s->quant[level][2]);
495 put_vc2_ue_uint(&s->pb, s->quant[level][3]);
496 }
497 }
498 }
499
500 /* VC-2 12.3 - transform_parameters() */
encode_transform_params(VC2EncContext *s)501 static void encode_transform_params(VC2EncContext *s)
502 {
503 put_vc2_ue_uint(&s->pb, s->wavelet_idx);
504 put_vc2_ue_uint(&s->pb, s->wavelet_depth);
505
506 encode_slice_params(s);
507 encode_quant_matrix(s);
508 }
509
510 /* VC-2 12.2 - wavelet_transform() */
encode_wavelet_transform(VC2EncContext *s)511 static void encode_wavelet_transform(VC2EncContext *s)
512 {
513 encode_transform_params(s);
514 align_put_bits(&s->pb);
515 }
516
517 /* VC-2 12 - picture_parse() */
encode_picture_start(VC2EncContext *s)518 static void encode_picture_start(VC2EncContext *s)
519 {
520 align_put_bits(&s->pb);
521 encode_picture_header(s);
522 align_put_bits(&s->pb);
523 encode_wavelet_transform(s);
524 }
525
526 #define QUANT(c, mul, add, shift) (((mul) * (c) + (add)) >> (shift))
527
528 /* VC-2 13.5.5.2 - slice_band() */
encode_subband(VC2EncContext *s, PutBitContext *pb, int sx, int sy, SubBand *b, int quant)529 static void encode_subband(VC2EncContext *s, PutBitContext *pb, int sx, int sy,
530 SubBand *b, int quant)
531 {
532 int x, y;
533
534 const int left = b->width * (sx+0) / s->num_x;
535 const int right = b->width * (sx+1) / s->num_x;
536 const int top = b->height * (sy+0) / s->num_y;
537 const int bottom = b->height * (sy+1) / s->num_y;
538
539 dwtcoef *coeff = b->buf + top * b->stride;
540 const uint64_t q_m = ((uint64_t)(s->qmagic_lut[quant][0])) << 2;
541 const uint64_t q_a = s->qmagic_lut[quant][1];
542 const int q_s = av_log2(ff_dirac_qscale_tab[quant]) + 32;
543
544 for (y = top; y < bottom; y++) {
545 for (x = left; x < right; x++) {
546 uint32_t c_abs = QUANT(FFABS(coeff[x]), q_m, q_a, q_s);
547 put_vc2_ue_uint(pb, c_abs);
548 if (c_abs)
549 put_bits(pb, 1, coeff[x] < 0);
550 }
551 coeff += b->stride;
552 }
553 }
554
count_hq_slice(SliceArgs *slice, int quant_idx)555 static int count_hq_slice(SliceArgs *slice, int quant_idx)
556 {
557 int x, y;
558 uint8_t quants[MAX_DWT_LEVELS][4];
559 int bits = 0, p, level, orientation;
560 VC2EncContext *s = slice->ctx;
561
562 if (slice->cache[quant_idx])
563 return slice->cache[quant_idx];
564
565 bits += 8*s->prefix_bytes;
566 bits += 8; /* quant_idx */
567
568 for (level = 0; level < s->wavelet_depth; level++)
569 for (orientation = !!level; orientation < 4; orientation++)
570 quants[level][orientation] = FFMAX(quant_idx - s->quant[level][orientation], 0);
571
572 for (p = 0; p < 3; p++) {
573 int bytes_start, bytes_len, pad_s, pad_c;
574 bytes_start = bits >> 3;
575 bits += 8;
576 for (level = 0; level < s->wavelet_depth; level++) {
577 for (orientation = !!level; orientation < 4; orientation++) {
578 SubBand *b = &s->plane[p].band[level][orientation];
579
580 const int q_idx = quants[level][orientation];
581 const uint64_t q_m = ((uint64_t)s->qmagic_lut[q_idx][0]) << 2;
582 const uint64_t q_a = s->qmagic_lut[q_idx][1];
583 const int q_s = av_log2(ff_dirac_qscale_tab[q_idx]) + 32;
584
585 const int left = b->width * slice->x / s->num_x;
586 const int right = b->width *(slice->x+1) / s->num_x;
587 const int top = b->height * slice->y / s->num_y;
588 const int bottom = b->height *(slice->y+1) / s->num_y;
589
590 dwtcoef *buf = b->buf + top * b->stride;
591
592 for (y = top; y < bottom; y++) {
593 for (x = left; x < right; x++) {
594 uint32_t c_abs = QUANT(FFABS(buf[x]), q_m, q_a, q_s);
595 bits += count_vc2_ue_uint(c_abs);
596 bits += !!c_abs;
597 }
598 buf += b->stride;
599 }
600 }
601 }
602 bits += FFALIGN(bits, 8) - bits;
603 bytes_len = (bits >> 3) - bytes_start - 1;
604 pad_s = FFALIGN(bytes_len, s->size_scaler)/s->size_scaler;
605 pad_c = (pad_s*s->size_scaler) - bytes_len;
606 bits += pad_c*8;
607 }
608
609 slice->cache[quant_idx] = bits;
610
611 return bits;
612 }
613
614 /* Approaches the best possible quantizer asymptotically, its kinda exaustive
615 * but we have a LUT to get the coefficient size in bits. Guaranteed to never
616 * overshoot, which is apparently very important when streaming */
rate_control(AVCodecContext *avctx, void *arg)617 static int rate_control(AVCodecContext *avctx, void *arg)
618 {
619 SliceArgs *slice_dat = arg;
620 VC2EncContext *s = slice_dat->ctx;
621 const int top = slice_dat->bits_ceil;
622 const int bottom = slice_dat->bits_floor;
623 int quant_buf[2] = {-1, -1};
624 int quant = slice_dat->quant_idx, step = 1;
625 int bits_last, bits = count_hq_slice(slice_dat, quant);
626 while ((bits > top) || (bits < bottom)) {
627 const int signed_step = bits > top ? +step : -step;
628 quant = av_clip(quant + signed_step, 0, s->q_ceil-1);
629 bits = count_hq_slice(slice_dat, quant);
630 if (quant_buf[1] == quant) {
631 quant = FFMAX(quant_buf[0], quant);
632 bits = quant == quant_buf[0] ? bits_last : bits;
633 break;
634 }
635 step = av_clip(step/2, 1, (s->q_ceil-1)/2);
636 quant_buf[1] = quant_buf[0];
637 quant_buf[0] = quant;
638 bits_last = bits;
639 }
640 slice_dat->quant_idx = av_clip(quant, 0, s->q_ceil-1);
641 slice_dat->bytes = SSIZE_ROUND(bits >> 3);
642 return 0;
643 }
644
calc_slice_sizes(VC2EncContext *s)645 static int calc_slice_sizes(VC2EncContext *s)
646 {
647 int i, j, slice_x, slice_y, bytes_left = 0;
648 int bytes_top[SLICE_REDIST_TOTAL] = {0};
649 int64_t total_bytes_needed = 0;
650 int slice_redist_range = FFMIN(SLICE_REDIST_TOTAL, s->num_x*s->num_y);
651 SliceArgs *enc_args = s->slice_args;
652 SliceArgs *top_loc[SLICE_REDIST_TOTAL] = {NULL};
653
654 init_quant_matrix(s);
655
656 for (slice_y = 0; slice_y < s->num_y; slice_y++) {
657 for (slice_x = 0; slice_x < s->num_x; slice_x++) {
658 SliceArgs *args = &enc_args[s->num_x*slice_y + slice_x];
659 args->ctx = s;
660 args->x = slice_x;
661 args->y = slice_y;
662 args->bits_ceil = s->slice_max_bytes << 3;
663 args->bits_floor = s->slice_min_bytes << 3;
664 memset(args->cache, 0, s->q_ceil*sizeof(*args->cache));
665 }
666 }
667
668 /* First pass - determine baseline slice sizes w.r.t. max_slice_size */
669 s->avctx->execute(s->avctx, rate_control, enc_args, NULL, s->num_x*s->num_y,
670 sizeof(SliceArgs));
671
672 for (i = 0; i < s->num_x*s->num_y; i++) {
673 SliceArgs *args = &enc_args[i];
674 bytes_left += args->bytes;
675 for (j = 0; j < slice_redist_range; j++) {
676 if (args->bytes > bytes_top[j]) {
677 bytes_top[j] = args->bytes;
678 top_loc[j] = args;
679 break;
680 }
681 }
682 }
683
684 bytes_left = s->frame_max_bytes - bytes_left;
685
686 /* Second pass - distribute leftover bytes */
687 while (bytes_left > 0) {
688 int distributed = 0;
689 for (i = 0; i < slice_redist_range; i++) {
690 SliceArgs *args;
691 int bits, bytes, diff, prev_bytes, new_idx;
692 if (bytes_left <= 0)
693 break;
694 if (!top_loc[i] || !top_loc[i]->quant_idx)
695 break;
696 args = top_loc[i];
697 prev_bytes = args->bytes;
698 new_idx = FFMAX(args->quant_idx - 1, 0);
699 bits = count_hq_slice(args, new_idx);
700 bytes = SSIZE_ROUND(bits >> 3);
701 diff = bytes - prev_bytes;
702 if ((bytes_left - diff) > 0) {
703 args->quant_idx = new_idx;
704 args->bytes = bytes;
705 bytes_left -= diff;
706 distributed++;
707 }
708 }
709 if (!distributed)
710 break;
711 }
712
713 for (i = 0; i < s->num_x*s->num_y; i++) {
714 SliceArgs *args = &enc_args[i];
715 total_bytes_needed += args->bytes;
716 s->q_avg = (s->q_avg + args->quant_idx)/2;
717 }
718
719 return total_bytes_needed;
720 }
721
722 /* VC-2 13.5.3 - hq_slice */
encode_hq_slice(AVCodecContext *avctx, void *arg)723 static int encode_hq_slice(AVCodecContext *avctx, void *arg)
724 {
725 SliceArgs *slice_dat = arg;
726 VC2EncContext *s = slice_dat->ctx;
727 PutBitContext *pb = &slice_dat->pb;
728 const int slice_x = slice_dat->x;
729 const int slice_y = slice_dat->y;
730 const int quant_idx = slice_dat->quant_idx;
731 const int slice_bytes_max = slice_dat->bytes;
732 uint8_t quants[MAX_DWT_LEVELS][4];
733 int p, level, orientation;
734
735 /* The reference decoder ignores it, and its typical length is 0 */
736 memset(put_bits_ptr(pb), 0, s->prefix_bytes);
737 skip_put_bytes(pb, s->prefix_bytes);
738
739 put_bits(pb, 8, quant_idx);
740
741 /* Slice quantization (slice_quantizers() in the specs) */
742 for (level = 0; level < s->wavelet_depth; level++)
743 for (orientation = !!level; orientation < 4; orientation++)
744 quants[level][orientation] = FFMAX(quant_idx - s->quant[level][orientation], 0);
745
746 /* Luma + 2 Chroma planes */
747 for (p = 0; p < 3; p++) {
748 int bytes_start, bytes_len, pad_s, pad_c;
749 bytes_start = put_bits_count(pb) >> 3;
750 put_bits(pb, 8, 0);
751 for (level = 0; level < s->wavelet_depth; level++) {
752 for (orientation = !!level; orientation < 4; orientation++) {
753 encode_subband(s, pb, slice_x, slice_y,
754 &s->plane[p].band[level][orientation],
755 quants[level][orientation]);
756 }
757 }
758 align_put_bits(pb);
759 bytes_len = (put_bits_count(pb) >> 3) - bytes_start - 1;
760 if (p == 2) {
761 int len_diff = slice_bytes_max - (put_bits_count(pb) >> 3);
762 pad_s = FFALIGN((bytes_len + len_diff), s->size_scaler)/s->size_scaler;
763 pad_c = (pad_s*s->size_scaler) - bytes_len;
764 } else {
765 pad_s = FFALIGN(bytes_len, s->size_scaler)/s->size_scaler;
766 pad_c = (pad_s*s->size_scaler) - bytes_len;
767 }
768 pb->buf[bytes_start] = pad_s;
769 flush_put_bits(pb);
770 /* vc2-reference uses that padding that decodes to '0' coeffs */
771 memset(put_bits_ptr(pb), 0xFF, pad_c);
772 skip_put_bytes(pb, pad_c);
773 }
774
775 return 0;
776 }
777
778 /* VC-2 13.5.1 - low_delay_transform_data() */
encode_slices(VC2EncContext *s)779 static int encode_slices(VC2EncContext *s)
780 {
781 uint8_t *buf;
782 int slice_x, slice_y, skip = 0;
783 SliceArgs *enc_args = s->slice_args;
784
785 flush_put_bits(&s->pb);
786 buf = put_bits_ptr(&s->pb);
787
788 for (slice_y = 0; slice_y < s->num_y; slice_y++) {
789 for (slice_x = 0; slice_x < s->num_x; slice_x++) {
790 SliceArgs *args = &enc_args[s->num_x*slice_y + slice_x];
791 init_put_bits(&args->pb, buf + skip, args->bytes+s->prefix_bytes);
792 skip += args->bytes;
793 }
794 }
795
796 s->avctx->execute(s->avctx, encode_hq_slice, enc_args, NULL, s->num_x*s->num_y,
797 sizeof(SliceArgs));
798
799 skip_put_bytes(&s->pb, skip);
800
801 return 0;
802 }
803
804 /*
805 * Transform basics for a 3 level transform
806 * |---------------------------------------------------------------------|
807 * | LL-0 | HL-0 | | |
808 * |--------|-------| HL-1 | |
809 * | LH-0 | HH-0 | | |
810 * |----------------|-----------------| HL-2 |
811 * | | | |
812 * | LH-1 | HH-1 | |
813 * | | | |
814 * |----------------------------------|----------------------------------|
815 * | | |
816 * | | |
817 * | | |
818 * | LH-2 | HH-2 |
819 * | | |
820 * | | |
821 * | | |
822 * |---------------------------------------------------------------------|
823 *
824 * DWT transforms are generally applied by splitting the image in two vertically
825 * and applying a low pass transform on the left part and a corresponding high
826 * pass transform on the right hand side. This is known as the horizontal filter
827 * stage.
828 * After that, the same operation is performed except the image is divided
829 * horizontally, with the high pass on the lower and the low pass on the higher
830 * side.
831 * Therefore, you're left with 4 subdivisions - known as low-low, low-high,
832 * high-low and high-high. They're referred to as orientations in the decoder
833 * and encoder.
834 *
835 * The LL (low-low) area contains the original image downsampled by the amount
836 * of levels. The rest of the areas can be thought as the details needed
837 * to restore the image perfectly to its original size.
838 */
dwt_plane(AVCodecContext *avctx, void *arg)839 static int dwt_plane(AVCodecContext *avctx, void *arg)
840 {
841 TransformArgs *transform_dat = arg;
842 VC2EncContext *s = transform_dat->ctx;
843 const void *frame_data = transform_dat->idata;
844 const ptrdiff_t linesize = transform_dat->istride;
845 const int field = transform_dat->field;
846 const Plane *p = transform_dat->plane;
847 VC2TransformContext *t = &transform_dat->t;
848 dwtcoef *buf = p->coef_buf;
849 const int idx = s->wavelet_idx;
850 const int skip = 1 + s->interlaced;
851
852 int x, y, level, offset;
853 ptrdiff_t pix_stride = linesize >> (s->bpp - 1);
854
855 if (field == 1) {
856 offset = 0;
857 pix_stride <<= 1;
858 } else if (field == 2) {
859 offset = pix_stride;
860 pix_stride <<= 1;
861 } else {
862 offset = 0;
863 }
864
865 if (s->bpp == 1) {
866 const uint8_t *pix = (const uint8_t *)frame_data + offset;
867 for (y = 0; y < p->height*skip; y+=skip) {
868 for (x = 0; x < p->width; x++) {
869 buf[x] = pix[x] - s->diff_offset;
870 }
871 memset(&buf[x], 0, (p->coef_stride - p->width)*sizeof(dwtcoef));
872 buf += p->coef_stride;
873 pix += pix_stride;
874 }
875 } else {
876 const uint16_t *pix = (const uint16_t *)frame_data + offset;
877 for (y = 0; y < p->height*skip; y+=skip) {
878 for (x = 0; x < p->width; x++) {
879 buf[x] = pix[x] - s->diff_offset;
880 }
881 memset(&buf[x], 0, (p->coef_stride - p->width)*sizeof(dwtcoef));
882 buf += p->coef_stride;
883 pix += pix_stride;
884 }
885 }
886
887 memset(buf, 0, p->coef_stride * (p->dwt_height - p->height) * sizeof(dwtcoef));
888
889 for (level = s->wavelet_depth-1; level >= 0; level--) {
890 const SubBand *b = &p->band[level][0];
891 t->vc2_subband_dwt[idx](t, p->coef_buf, p->coef_stride,
892 b->width, b->height);
893 }
894
895 return 0;
896 }
897
encode_frame(VC2EncContext *s, AVPacket *avpkt, const AVFrame *frame, const char *aux_data, const int header_size, int field)898 static int encode_frame(VC2EncContext *s, AVPacket *avpkt, const AVFrame *frame,
899 const char *aux_data, const int header_size, int field)
900 {
901 int i, ret;
902 int64_t max_frame_bytes;
903
904 /* Threaded DWT transform */
905 for (i = 0; i < 3; i++) {
906 s->transform_args[i].ctx = s;
907 s->transform_args[i].field = field;
908 s->transform_args[i].plane = &s->plane[i];
909 s->transform_args[i].idata = frame->data[i];
910 s->transform_args[i].istride = frame->linesize[i];
911 }
912 s->avctx->execute(s->avctx, dwt_plane, s->transform_args, NULL, 3,
913 sizeof(TransformArgs));
914
915 /* Calculate per-slice quantizers and sizes */
916 max_frame_bytes = header_size + calc_slice_sizes(s);
917
918 if (field < 2) {
919 ret = ff_get_encode_buffer(s->avctx, avpkt,
920 max_frame_bytes << s->interlaced, 0);
921 if (ret) {
922 av_log(s->avctx, AV_LOG_ERROR, "Error getting output packet.\n");
923 return ret;
924 }
925 init_put_bits(&s->pb, avpkt->data, avpkt->size);
926 }
927
928 /* Sequence header */
929 encode_parse_info(s, DIRAC_PCODE_SEQ_HEADER);
930 encode_seq_header(s);
931
932 /* Encoder version */
933 if (aux_data) {
934 encode_parse_info(s, DIRAC_PCODE_AUX);
935 ff_put_string(&s->pb, aux_data, 1);
936 }
937
938 /* Picture header */
939 encode_parse_info(s, DIRAC_PCODE_PICTURE_HQ);
940 encode_picture_start(s);
941
942 /* Encode slices */
943 encode_slices(s);
944
945 /* End sequence */
946 encode_parse_info(s, DIRAC_PCODE_END_SEQ);
947
948 return 0;
949 }
950
vc2_encode_frame(AVCodecContext *avctx, AVPacket *avpkt, const AVFrame *frame, int *got_packet)951 static av_cold int vc2_encode_frame(AVCodecContext *avctx, AVPacket *avpkt,
952 const AVFrame *frame, int *got_packet)
953 {
954 int ret = 0;
955 int slice_ceil, sig_size = 256;
956 VC2EncContext *s = avctx->priv_data;
957 const int bitexact = avctx->flags & AV_CODEC_FLAG_BITEXACT;
958 const char *aux_data = bitexact ? "Lavc" : LIBAVCODEC_IDENT;
959 const int aux_data_size = bitexact ? sizeof("Lavc") : sizeof(LIBAVCODEC_IDENT);
960 const int header_size = 100 + aux_data_size;
961 int64_t r_bitrate = avctx->bit_rate >> (s->interlaced);
962
963 s->avctx = avctx;
964 s->size_scaler = 2;
965 s->prefix_bytes = 0;
966 s->last_parse_code = 0;
967 s->next_parse_offset = 0;
968
969 /* Rate control */
970 s->frame_max_bytes = (av_rescale(r_bitrate, s->avctx->time_base.num,
971 s->avctx->time_base.den) >> 3) - header_size;
972 s->slice_max_bytes = slice_ceil = av_rescale(s->frame_max_bytes, 1, s->num_x*s->num_y);
973
974 /* Find an appropriate size scaler */
975 while (sig_size > 255) {
976 int r_size = SSIZE_ROUND(s->slice_max_bytes);
977 if (r_size > slice_ceil) {
978 s->slice_max_bytes -= r_size - slice_ceil;
979 r_size = SSIZE_ROUND(s->slice_max_bytes);
980 }
981 sig_size = r_size/s->size_scaler; /* Signalled slize size */
982 s->size_scaler <<= 1;
983 }
984
985 s->slice_min_bytes = s->slice_max_bytes - s->slice_max_bytes*(s->tolerance/100.0f);
986 if (s->slice_min_bytes < 0)
987 return AVERROR(EINVAL);
988
989 ret = encode_frame(s, avpkt, frame, aux_data, header_size, s->interlaced);
990 if (ret)
991 return ret;
992 if (s->interlaced) {
993 ret = encode_frame(s, avpkt, frame, aux_data, header_size, 2);
994 if (ret)
995 return ret;
996 }
997
998 flush_put_bits(&s->pb);
999 av_shrink_packet(avpkt, put_bytes_output(&s->pb));
1000
1001 *got_packet = 1;
1002
1003 return 0;
1004 }
1005
vc2_encode_end(AVCodecContext *avctx)1006 static av_cold int vc2_encode_end(AVCodecContext *avctx)
1007 {
1008 int i;
1009 VC2EncContext *s = avctx->priv_data;
1010
1011 av_log(avctx, AV_LOG_INFO, "Qavg: %i\n", s->q_avg);
1012
1013 for (i = 0; i < 3; i++) {
1014 ff_vc2enc_free_transforms(&s->transform_args[i].t);
1015 av_freep(&s->plane[i].coef_buf);
1016 }
1017
1018 av_freep(&s->slice_args);
1019
1020 return 0;
1021 }
1022
vc2_encode_init(AVCodecContext *avctx)1023 static av_cold int vc2_encode_init(AVCodecContext *avctx)
1024 {
1025 Plane *p;
1026 SubBand *b;
1027 int i, level, o, shift, ret;
1028 const AVPixFmtDescriptor *fmt = av_pix_fmt_desc_get(avctx->pix_fmt);
1029 const int depth = fmt->comp[0].depth;
1030 VC2EncContext *s = avctx->priv_data;
1031
1032 s->picture_number = 0;
1033
1034 /* Total allowed quantization range */
1035 s->q_ceil = DIRAC_MAX_QUANT_INDEX;
1036
1037 s->ver.major = 2;
1038 s->ver.minor = 0;
1039 s->profile = 3;
1040 s->level = 3;
1041
1042 s->base_vf = -1;
1043 s->strict_compliance = 1;
1044
1045 s->q_avg = 0;
1046 s->slice_max_bytes = 0;
1047 s->slice_min_bytes = 0;
1048
1049 /* Mark unknown as progressive */
1050 s->interlaced = !((avctx->field_order == AV_FIELD_UNKNOWN) ||
1051 (avctx->field_order == AV_FIELD_PROGRESSIVE));
1052
1053 for (i = 0; i < base_video_fmts_len; i++) {
1054 const VC2BaseVideoFormat *fmt = &base_video_fmts[i];
1055 if (avctx->pix_fmt != fmt->pix_fmt)
1056 continue;
1057 if (avctx->time_base.num != fmt->time_base.num)
1058 continue;
1059 if (avctx->time_base.den != fmt->time_base.den)
1060 continue;
1061 if (avctx->width != fmt->width)
1062 continue;
1063 if (avctx->height != fmt->height)
1064 continue;
1065 if (s->interlaced != fmt->interlaced)
1066 continue;
1067 s->base_vf = i;
1068 s->level = base_video_fmts[i].level;
1069 break;
1070 }
1071
1072 if (s->interlaced)
1073 av_log(avctx, AV_LOG_WARNING, "Interlacing enabled!\n");
1074
1075 if ((s->slice_width & (s->slice_width - 1)) ||
1076 (s->slice_height & (s->slice_height - 1))) {
1077 av_log(avctx, AV_LOG_ERROR, "Slice size is not a power of two!\n");
1078 return AVERROR_UNKNOWN;
1079 }
1080
1081 if ((s->slice_width > avctx->width) ||
1082 (s->slice_height > avctx->height)) {
1083 av_log(avctx, AV_LOG_ERROR, "Slice size is bigger than the image!\n");
1084 return AVERROR_UNKNOWN;
1085 }
1086
1087 if (s->base_vf <= 0) {
1088 if (avctx->strict_std_compliance < FF_COMPLIANCE_STRICT) {
1089 s->strict_compliance = s->base_vf = 0;
1090 av_log(avctx, AV_LOG_WARNING, "Format does not strictly comply with VC2 specs\n");
1091 } else {
1092 av_log(avctx, AV_LOG_WARNING, "Given format does not strictly comply with "
1093 "the specifications, decrease strictness to use it.\n");
1094 return AVERROR_UNKNOWN;
1095 }
1096 } else {
1097 av_log(avctx, AV_LOG_INFO, "Selected base video format = %i (%s)\n",
1098 s->base_vf, base_video_fmts[s->base_vf].name);
1099 }
1100
1101 /* Chroma subsampling */
1102 ret = av_pix_fmt_get_chroma_sub_sample(avctx->pix_fmt, &s->chroma_x_shift, &s->chroma_y_shift);
1103 if (ret)
1104 return ret;
1105
1106 /* Bit depth and color range index */
1107 if (depth == 8 && avctx->color_range == AVCOL_RANGE_JPEG) {
1108 s->bpp = 1;
1109 s->bpp_idx = 1;
1110 s->diff_offset = 128;
1111 } else if (depth == 8 && (avctx->color_range == AVCOL_RANGE_MPEG ||
1112 avctx->color_range == AVCOL_RANGE_UNSPECIFIED)) {
1113 s->bpp = 1;
1114 s->bpp_idx = 2;
1115 s->diff_offset = 128;
1116 } else if (depth == 10) {
1117 s->bpp = 2;
1118 s->bpp_idx = 3;
1119 s->diff_offset = 512;
1120 } else {
1121 s->bpp = 2;
1122 s->bpp_idx = 4;
1123 s->diff_offset = 2048;
1124 }
1125
1126 /* Planes initialization */
1127 for (i = 0; i < 3; i++) {
1128 int w, h;
1129 p = &s->plane[i];
1130 p->width = avctx->width >> (i ? s->chroma_x_shift : 0);
1131 p->height = avctx->height >> (i ? s->chroma_y_shift : 0);
1132 if (s->interlaced)
1133 p->height >>= 1;
1134 p->dwt_width = w = FFALIGN(p->width, (1 << s->wavelet_depth));
1135 p->dwt_height = h = FFALIGN(p->height, (1 << s->wavelet_depth));
1136 p->coef_stride = FFALIGN(p->dwt_width, 32);
1137 p->coef_buf = av_mallocz(p->coef_stride*p->dwt_height*sizeof(dwtcoef));
1138 if (!p->coef_buf)
1139 return AVERROR(ENOMEM);
1140 for (level = s->wavelet_depth-1; level >= 0; level--) {
1141 w = w >> 1;
1142 h = h >> 1;
1143 for (o = 0; o < 4; o++) {
1144 b = &p->band[level][o];
1145 b->width = w;
1146 b->height = h;
1147 b->stride = p->coef_stride;
1148 shift = (o > 1)*b->height*b->stride + (o & 1)*b->width;
1149 b->buf = p->coef_buf + shift;
1150 }
1151 }
1152
1153 /* DWT init */
1154 if (ff_vc2enc_init_transforms(&s->transform_args[i].t,
1155 s->plane[i].coef_stride,
1156 s->plane[i].dwt_height,
1157 s->slice_width, s->slice_height))
1158 return AVERROR(ENOMEM);
1159 }
1160
1161 /* Slices */
1162 s->num_x = s->plane[0].dwt_width/s->slice_width;
1163 s->num_y = s->plane[0].dwt_height/s->slice_height;
1164
1165 s->slice_args = av_calloc(s->num_x*s->num_y, sizeof(SliceArgs));
1166 if (!s->slice_args)
1167 return AVERROR(ENOMEM);
1168
1169 for (i = 0; i < 116; i++) {
1170 const uint64_t qf = ff_dirac_qscale_tab[i];
1171 const uint32_t m = av_log2(qf);
1172 const uint32_t t = (1ULL << (m + 32)) / qf;
1173 const uint32_t r = (t*qf + qf) & UINT32_MAX;
1174 if (!(qf & (qf - 1))) {
1175 s->qmagic_lut[i][0] = 0xFFFFFFFF;
1176 s->qmagic_lut[i][1] = 0xFFFFFFFF;
1177 } else if (r <= 1 << m) {
1178 s->qmagic_lut[i][0] = t + 1;
1179 s->qmagic_lut[i][1] = 0;
1180 } else {
1181 s->qmagic_lut[i][0] = t;
1182 s->qmagic_lut[i][1] = t;
1183 }
1184 }
1185
1186 return 0;
1187 }
1188
1189 #define VC2ENC_FLAGS (AV_OPT_FLAG_ENCODING_PARAM | AV_OPT_FLAG_VIDEO_PARAM)
1190 static const AVOption vc2enc_options[] = {
1191 {"tolerance", "Max undershoot in percent", offsetof(VC2EncContext, tolerance), AV_OPT_TYPE_DOUBLE, {.dbl = 5.0f}, 0.0f, 45.0f, VC2ENC_FLAGS, "tolerance"},
1192 {"slice_width", "Slice width", offsetof(VC2EncContext, slice_width), AV_OPT_TYPE_INT, {.i64 = 32}, 32, 1024, VC2ENC_FLAGS, "slice_width"},
1193 {"slice_height", "Slice height", offsetof(VC2EncContext, slice_height), AV_OPT_TYPE_INT, {.i64 = 16}, 8, 1024, VC2ENC_FLAGS, "slice_height"},
1194 {"wavelet_depth", "Transform depth", offsetof(VC2EncContext, wavelet_depth), AV_OPT_TYPE_INT, {.i64 = 4}, 1, 5, VC2ENC_FLAGS, "wavelet_depth"},
1195 {"wavelet_type", "Transform type", offsetof(VC2EncContext, wavelet_idx), AV_OPT_TYPE_INT, {.i64 = VC2_TRANSFORM_9_7}, 0, VC2_TRANSFORMS_NB, VC2ENC_FLAGS, "wavelet_idx"},
1196 {"9_7", "Deslauriers-Dubuc (9,7)", 0, AV_OPT_TYPE_CONST, {.i64 = VC2_TRANSFORM_9_7}, INT_MIN, INT_MAX, VC2ENC_FLAGS, "wavelet_idx"},
1197 {"5_3", "LeGall (5,3)", 0, AV_OPT_TYPE_CONST, {.i64 = VC2_TRANSFORM_5_3}, INT_MIN, INT_MAX, VC2ENC_FLAGS, "wavelet_idx"},
1198 {"haar", "Haar (with shift)", 0, AV_OPT_TYPE_CONST, {.i64 = VC2_TRANSFORM_HAAR_S}, INT_MIN, INT_MAX, VC2ENC_FLAGS, "wavelet_idx"},
1199 {"haar_noshift", "Haar (without shift)", 0, AV_OPT_TYPE_CONST, {.i64 = VC2_TRANSFORM_HAAR}, INT_MIN, INT_MAX, VC2ENC_FLAGS, "wavelet_idx"},
1200 {"qm", "Custom quantization matrix", offsetof(VC2EncContext, quant_matrix), AV_OPT_TYPE_INT, {.i64 = VC2_QM_DEF}, 0, VC2_QM_NB, VC2ENC_FLAGS, "quant_matrix"},
1201 {"default", "Default from the specifications", 0, AV_OPT_TYPE_CONST, {.i64 = VC2_QM_DEF}, INT_MIN, INT_MAX, VC2ENC_FLAGS, "quant_matrix"},
1202 {"color", "Prevents low bitrate discoloration", 0, AV_OPT_TYPE_CONST, {.i64 = VC2_QM_COL}, INT_MIN, INT_MAX, VC2ENC_FLAGS, "quant_matrix"},
1203 {"flat", "Optimize for PSNR", 0, AV_OPT_TYPE_CONST, {.i64 = VC2_QM_FLAT}, INT_MIN, INT_MAX, VC2ENC_FLAGS, "quant_matrix"},
1204 {NULL}
1205 };
1206
1207 static const AVClass vc2enc_class = {
1208 .class_name = "SMPTE VC-2 encoder",
1209 .category = AV_CLASS_CATEGORY_ENCODER,
1210 .option = vc2enc_options,
1211 .item_name = av_default_item_name,
1212 .version = LIBAVUTIL_VERSION_INT
1213 };
1214
1215 static const FFCodecDefault vc2enc_defaults[] = {
1216 { "b", "600000000" },
1217 { NULL },
1218 };
1219
1220 static const enum AVPixelFormat allowed_pix_fmts[] = {
1221 AV_PIX_FMT_YUV420P, AV_PIX_FMT_YUV422P, AV_PIX_FMT_YUV444P,
1222 AV_PIX_FMT_YUV420P10, AV_PIX_FMT_YUV422P10, AV_PIX_FMT_YUV444P10,
1223 AV_PIX_FMT_YUV420P12, AV_PIX_FMT_YUV422P12, AV_PIX_FMT_YUV444P12,
1224 AV_PIX_FMT_NONE
1225 };
1226
1227 const FFCodec ff_vc2_encoder = {
1228 .p.name = "vc2",
1229 .p.long_name = NULL_IF_CONFIG_SMALL("SMPTE VC-2"),
1230 .p.type = AVMEDIA_TYPE_VIDEO,
1231 .p.id = AV_CODEC_ID_DIRAC,
1232 .p.capabilities = AV_CODEC_CAP_DR1 | AV_CODEC_CAP_SLICE_THREADS,
1233 .caps_internal = FF_CODEC_CAP_INIT_THREADSAFE | FF_CODEC_CAP_INIT_CLEANUP,
1234 .priv_data_size = sizeof(VC2EncContext),
1235 .init = vc2_encode_init,
1236 .close = vc2_encode_end,
1237 FF_CODEC_ENCODE_CB(vc2_encode_frame),
1238 .p.priv_class = &vc2enc_class,
1239 .defaults = vc2enc_defaults,
1240 .p.pix_fmts = allowed_pix_fmts
1241 };
1242