Go to the documentation of this file. 1 /*
2 * vMix decoder
3 * Copyright (c) 2023 Paul B Mahol
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 <stdio.h>
23 #include <stdlib.h>
24 #include <string.h>
25
29
32 #define CACHED_BITSTREAM_READER !ARCH_X86_32
37
44
48
51
54
57
59 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
60 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
61 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
62 1, 1, 1, 1, 1, 1,64,63,62,61,
63 60,59,58,57,56,55,54,53,52,51,
64 50,49,48,47,46,45,44,43,42,41,
65 40,39,38,37,36,35,34,33,32,31,
66 30,29,28,27,26,25,24,23,22,21,
67 20,19,18,17,16,15,14,13,12,11,
68 10, 9, 8, 7, 6, 5, 4, 3, 2, 1,
69 };
70
71 static const uint8_t
quant[64] = {
72 16, 16, 19, 22, 22, 26, 26, 27,
73 16, 16, 22, 22, 26, 27, 27, 29,
74 19, 22, 26, 26, 27, 29, 29, 35,
75 22, 24, 27, 27, 29, 32, 34, 38,
76 26, 27, 29, 29, 32, 35, 38, 46,
77 27, 29, 34, 34, 35, 40, 46, 56,
78 29, 34, 34, 37, 40, 48, 56, 69,
79 34, 37, 38, 40, 48, 58, 69, 83,
80 };
81
83 {
85
88
91
94 s->idsp.idct_permutation);
95 return 0;
96 }
97
99 {
101 int sign = (buf & 1) - 1;
102 return ((buf >> 1) ^ (~sign));
103 }
104
107 unsigned *dcrun, unsigned *acrun,
109 {
110 const ptrdiff_t linesize =
frame->linesize[plane];
111 uint8_t *
dst =
frame->data[plane] + by * linesize;
112 unsigned dc_run = *dcrun, ac_run = *acrun;
115 const int16_t *factors =
s->factors;
116 const uint8_t *scan =
s->scan;
117 const int add = plane ? 0 : 1024;
118 int i, dc_v = 0, ac_v = 0,
dc = 0;
119 const int lshift =
s->lshift;
120
121 for (int y = 0; y < 2; y++) {
122 for (
int x = 0; x <
width; x += 8) {
124
125 if (dc_run > 0) {
126 dc_run--;
127 } else {
131 dc += (unsigned)dc_v;
132 if (!dc_v)
134 }
135
136 for (int n = 0; n < 64; n++) {
137 if (ac_run > 0) {
138 ac_run--;
139 continue;
140 }
141
146 block[
i] = ((unsigned)ac_v * factors[
i]) >> 4;
147 if (!ac_v)
149 }
150
151 block[0] = ((unsigned)
dc << lshift) + (unsigned)add;
152 s->idsp.idct_put(
dst + x, linesize,
block);
153 }
154
156 }
157
158 *dcrun = dc_run;
159 *acrun = ac_run;
160
161 return 0;
162 }
163
165 const uint8_t *dc_src, unsigned dc_slice_size,
166 const uint8_t *ac_src, unsigned ac_slice_size,
167 int by)
168 {
169 unsigned dc_run = 0, ac_run = 0;
172
176
180
181 for (
int p = 0;
p < 3;
p++) {
182 const int rshift = !!
p;
184 &dc_run, &ac_run,
frame,
185 frame->width >> rshift, by,
p);
188
193
196 }
197
202
203 return 0;
204 }
205
207 int n, int thread_nb)
208 {
210 const uint8_t *dc_slice_ptr =
s->slices[n].dc_ptr;
211 const uint8_t *ac_slice_ptr =
s->slices[n].ac_ptr;
212 unsigned dc_slice_size =
s->slices[n].dc_size;
213 unsigned ac_slice_size =
s->slices[n].ac_size;
215
217 ac_slice_ptr, ac_slice_size, n * 16);
218 }
219
223 {
227
228 if (avpkt->
size <= 7)
230
234 s->lshift = avpkt->
data[1];
237
240
242 for (int n = 0; n < 64; n++)
243 s->factors[n] =
quant[n] * q;
244
245 s->nb_slices = (avctx->
height + 15) / 16;
249
250 for (
int n = 0; n <
s->nb_slices; n++) {
251 unsigned slice_size;
252
255
257 if (slice_size > avpkt->
size)
259
262
263 s->slices[n].dc_size = slice_size;
266 }
267
268 for (
int n = 0; n <
s->nb_slices; n++) {
269 unsigned slice_size;
270
273
275 if (slice_size > avpkt->
size)
277
280
281 s->slices[n].ac_size = slice_size;
284 }
285
289
291
292 *got_frame = 1;
293
295 }
296
298 {
301 return 0;
302 }
303
315 };
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]