/
yuv_rgb.h
381 lines (316 loc) · 13.4 KB
/
yuv_rgb.h
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
// Copyright 2016 Adrien Descamps
// Distributed under BSD 3-Clause License
// Provide optimized functions to convert images from 8bits yuv420 to rgb24 format
// There are a few slightly different variations of the YCbCr color space with different parameters that
// change the conversion matrix.
// The three most common YCbCr color space, defined by BT.601, BT.709 and JPEG standard are implemented here.
// See the respective standards for details
// The matrix values used are derived from http://www.equasys.de/colorconversion.html
// YUV420 is stored as three separate channels, with U and V (Cb and Cr) subsampled by a 2 factor
// For conversion from yuv to rgb, no interpolation is done, and the same UV value are used for 4 rgb pixels. This
// is suboptimal for image quality, but by far the fastest method.
// For all methods, width and height should be even, if not, the last row/column of the result image won't be affected.
// For sse methods, if the width if not divisable by 32, the last (width%32) pixels of each line won't be affected.
#include "SDL_stdinc.h"
/*#include <stdint.h>*/
typedef enum
{
YCBCR_JPEG,
YCBCR_601,
YCBCR_709
} YCbCrType;
// yuv to rgb, standard c implementation
void yuv420_rgb565_std(
uint32_t width, uint32_t height,
const uint8_t *y, const uint8_t *u, const uint8_t *v, uint32_t y_stride, uint32_t uv_stride,
uint8_t *rgb, uint32_t rgb_stride,
YCbCrType yuv_type);
void yuv420_rgb24_std(
uint32_t width, uint32_t height,
const uint8_t *y, const uint8_t *u, const uint8_t *v, uint32_t y_stride, uint32_t uv_stride,
uint8_t *rgb, uint32_t rgb_stride,
YCbCrType yuv_type);
void yuv420_rgba_std(
uint32_t width, uint32_t height,
const uint8_t *y, const uint8_t *u, const uint8_t *v, uint32_t y_stride, uint32_t uv_stride,
uint8_t *rgb, uint32_t rgb_stride,
YCbCrType yuv_type);
void yuv420_bgra_std(
uint32_t width, uint32_t height,
const uint8_t *y, const uint8_t *u, const uint8_t *v, uint32_t y_stride, uint32_t uv_stride,
uint8_t *rgb, uint32_t rgb_stride,
YCbCrType yuv_type);
void yuv420_argb_std(
uint32_t width, uint32_t height,
const uint8_t *y, const uint8_t *u, const uint8_t *v, uint32_t y_stride, uint32_t uv_stride,
uint8_t *rgb, uint32_t rgb_stride,
YCbCrType yuv_type);
void yuv420_abgr_std(
uint32_t width, uint32_t height,
const uint8_t *y, const uint8_t *u, const uint8_t *v, uint32_t y_stride, uint32_t uv_stride,
uint8_t *rgb, uint32_t rgb_stride,
YCbCrType yuv_type);
void yuv422_rgb565_std(
uint32_t width, uint32_t height,
const uint8_t *y, const uint8_t *u, const uint8_t *v, uint32_t y_stride, uint32_t uv_stride,
uint8_t *rgb, uint32_t rgb_stride,
YCbCrType yuv_type);
void yuv422_rgb24_std(
uint32_t width, uint32_t height,
const uint8_t *y, const uint8_t *u, const uint8_t *v, uint32_t y_stride, uint32_t uv_stride,
uint8_t *rgb, uint32_t rgb_stride,
YCbCrType yuv_type);
void yuv422_rgba_std(
uint32_t width, uint32_t height,
const uint8_t *y, const uint8_t *u, const uint8_t *v, uint32_t y_stride, uint32_t uv_stride,
uint8_t *rgb, uint32_t rgb_stride,
YCbCrType yuv_type);
void yuv422_bgra_std(
uint32_t width, uint32_t height,
const uint8_t *y, const uint8_t *u, const uint8_t *v, uint32_t y_stride, uint32_t uv_stride,
uint8_t *rgb, uint32_t rgb_stride,
YCbCrType yuv_type);
void yuv422_argb_std(
uint32_t width, uint32_t height,
const uint8_t *y, const uint8_t *u, const uint8_t *v, uint32_t y_stride, uint32_t uv_stride,
uint8_t *rgb, uint32_t rgb_stride,
YCbCrType yuv_type);
void yuv422_abgr_std(
uint32_t width, uint32_t height,
const uint8_t *y, const uint8_t *u, const uint8_t *v, uint32_t y_stride, uint32_t uv_stride,
uint8_t *rgb, uint32_t rgb_stride,
YCbCrType yuv_type);
void yuvnv12_rgb565_std(
uint32_t width, uint32_t height,
const uint8_t *y, const uint8_t *u, const uint8_t *v, uint32_t y_stride, uint32_t uv_stride,
uint8_t *rgb, uint32_t rgb_stride,
YCbCrType yuv_type);
void yuvnv12_rgb24_std(
uint32_t width, uint32_t height,
const uint8_t *y, const uint8_t *u, const uint8_t *v, uint32_t y_stride, uint32_t uv_stride,
uint8_t *rgb, uint32_t rgb_stride,
YCbCrType yuv_type);
void yuvnv12_rgba_std(
uint32_t width, uint32_t height,
const uint8_t *y, const uint8_t *u, const uint8_t *v, uint32_t y_stride, uint32_t uv_stride,
uint8_t *rgb, uint32_t rgb_stride,
YCbCrType yuv_type);
void yuvnv12_bgra_std(
uint32_t width, uint32_t height,
const uint8_t *y, const uint8_t *u, const uint8_t *v, uint32_t y_stride, uint32_t uv_stride,
uint8_t *rgb, uint32_t rgb_stride,
YCbCrType yuv_type);
void yuvnv12_argb_std(
uint32_t width, uint32_t height,
const uint8_t *y, const uint8_t *u, const uint8_t *v, uint32_t y_stride, uint32_t uv_stride,
uint8_t *rgb, uint32_t rgb_stride,
YCbCrType yuv_type);
void yuvnv12_abgr_std(
uint32_t width, uint32_t height,
const uint8_t *y, const uint8_t *u, const uint8_t *v, uint32_t y_stride, uint32_t uv_stride,
uint8_t *rgb, uint32_t rgb_stride,
YCbCrType yuv_type);
// yuv to rgb, sse implementation
// pointers must be 16 byte aligned, and strides must be divisable by 16
void yuv420_rgb565_sse(
uint32_t width, uint32_t height,
const uint8_t *y, const uint8_t *u, const uint8_t *v, uint32_t y_stride, uint32_t uv_stride,
uint8_t *rgb, uint32_t rgb_stride,
YCbCrType yuv_type);
void yuv420_rgb24_sse(
uint32_t width, uint32_t height,
const uint8_t *y, const uint8_t *u, const uint8_t *v, uint32_t y_stride, uint32_t uv_stride,
uint8_t *rgb, uint32_t rgb_stride,
YCbCrType yuv_type);
void yuv420_rgba_sse(
uint32_t width, uint32_t height,
const uint8_t *y, const uint8_t *u, const uint8_t *v, uint32_t y_stride, uint32_t uv_stride,
uint8_t *rgb, uint32_t rgb_stride,
YCbCrType yuv_type);
void yuv420_bgra_sse(
uint32_t width, uint32_t height,
const uint8_t *y, const uint8_t *u, const uint8_t *v, uint32_t y_stride, uint32_t uv_stride,
uint8_t *rgb, uint32_t rgb_stride,
YCbCrType yuv_type);
void yuv420_argb_sse(
uint32_t width, uint32_t height,
const uint8_t *y, const uint8_t *u, const uint8_t *v, uint32_t y_stride, uint32_t uv_stride,
uint8_t *rgb, uint32_t rgb_stride,
YCbCrType yuv_type);
void yuv420_abgr_sse(
uint32_t width, uint32_t height,
const uint8_t *y, const uint8_t *u, const uint8_t *v, uint32_t y_stride, uint32_t uv_stride,
uint8_t *rgb, uint32_t rgb_stride,
YCbCrType yuv_type);
void yuv422_rgb565_sse(
uint32_t width, uint32_t height,
const uint8_t *y, const uint8_t *u, const uint8_t *v, uint32_t y_stride, uint32_t uv_stride,
uint8_t *rgb, uint32_t rgb_stride,
YCbCrType yuv_type);
void yuv422_rgb24_sse(
uint32_t width, uint32_t height,
const uint8_t *y, const uint8_t *u, const uint8_t *v, uint32_t y_stride, uint32_t uv_stride,
uint8_t *rgb, uint32_t rgb_stride,
YCbCrType yuv_type);
void yuv422_rgba_sse(
uint32_t width, uint32_t height,
const uint8_t *y, const uint8_t *u, const uint8_t *v, uint32_t y_stride, uint32_t uv_stride,
uint8_t *rgb, uint32_t rgb_stride,
YCbCrType yuv_type);
void yuv422_bgra_sse(
uint32_t width, uint32_t height,
const uint8_t *y, const uint8_t *u, const uint8_t *v, uint32_t y_stride, uint32_t uv_stride,
uint8_t *rgb, uint32_t rgb_stride,
YCbCrType yuv_type);
void yuv422_argb_sse(
uint32_t width, uint32_t height,
const uint8_t *y, const uint8_t *u, const uint8_t *v, uint32_t y_stride, uint32_t uv_stride,
uint8_t *rgb, uint32_t rgb_stride,
YCbCrType yuv_type);
void yuv422_abgr_sse(
uint32_t width, uint32_t height,
const uint8_t *y, const uint8_t *u, const uint8_t *v, uint32_t y_stride, uint32_t uv_stride,
uint8_t *rgb, uint32_t rgb_stride,
YCbCrType yuv_type);
void yuvnv12_rgb565_sse(
uint32_t width, uint32_t height,
const uint8_t *y, const uint8_t *u, const uint8_t *v, uint32_t y_stride, uint32_t uv_stride,
uint8_t *rgb, uint32_t rgb_stride,
YCbCrType yuv_type);
void yuvnv12_rgb24_sse(
uint32_t width, uint32_t height,
const uint8_t *y, const uint8_t *u, const uint8_t *v, uint32_t y_stride, uint32_t uv_stride,
uint8_t *rgb, uint32_t rgb_stride,
YCbCrType yuv_type);
void yuvnv12_rgba_sse(
uint32_t width, uint32_t height,
const uint8_t *y, const uint8_t *u, const uint8_t *v, uint32_t y_stride, uint32_t uv_stride,
uint8_t *rgb, uint32_t rgb_stride,
YCbCrType yuv_type);
void yuvnv12_bgra_sse(
uint32_t width, uint32_t height,
const uint8_t *y, const uint8_t *u, const uint8_t *v, uint32_t y_stride, uint32_t uv_stride,
uint8_t *rgb, uint32_t rgb_stride,
YCbCrType yuv_type);
void yuvnv12_argb_sse(
uint32_t width, uint32_t height,
const uint8_t *y, const uint8_t *u, const uint8_t *v, uint32_t y_stride, uint32_t uv_stride,
uint8_t *rgb, uint32_t rgb_stride,
YCbCrType yuv_type);
void yuvnv12_abgr_sse(
uint32_t width, uint32_t height,
const uint8_t *y, const uint8_t *u, const uint8_t *v, uint32_t y_stride, uint32_t uv_stride,
uint8_t *rgb, uint32_t rgb_stride,
YCbCrType yuv_type);
// yuv to rgb, sse implementation
// pointers do not need to be 16 byte aligned
void yuv420_rgb565_sseu(
uint32_t width, uint32_t height,
const uint8_t *y, const uint8_t *u, const uint8_t *v, uint32_t y_stride, uint32_t uv_stride,
uint8_t *rgb, uint32_t rgb_stride,
YCbCrType yuv_type);
void yuv420_rgb24_sseu(
uint32_t width, uint32_t height,
const uint8_t *y, const uint8_t *u, const uint8_t *v, uint32_t y_stride, uint32_t uv_stride,
uint8_t *rgb, uint32_t rgb_stride,
YCbCrType yuv_type);
void yuv420_rgba_sseu(
uint32_t width, uint32_t height,
const uint8_t *y, const uint8_t *u, const uint8_t *v, uint32_t y_stride, uint32_t uv_stride,
uint8_t *rgb, uint32_t rgb_stride,
YCbCrType yuv_type);
void yuv420_bgra_sseu(
uint32_t width, uint32_t height,
const uint8_t *y, const uint8_t *u, const uint8_t *v, uint32_t y_stride, uint32_t uv_stride,
uint8_t *rgb, uint32_t rgb_stride,
YCbCrType yuv_type);
void yuv420_argb_sseu(
uint32_t width, uint32_t height,
const uint8_t *y, const uint8_t *u, const uint8_t *v, uint32_t y_stride, uint32_t uv_stride,
uint8_t *rgb, uint32_t rgb_stride,
YCbCrType yuv_type);
void yuv420_abgr_sseu(
uint32_t width, uint32_t height,
const uint8_t *y, const uint8_t *u, const uint8_t *v, uint32_t y_stride, uint32_t uv_stride,
uint8_t *rgb, uint32_t rgb_stride,
YCbCrType yuv_type);
void yuv422_rgb565_sseu(
uint32_t width, uint32_t height,
const uint8_t *y, const uint8_t *u, const uint8_t *v, uint32_t y_stride, uint32_t uv_stride,
uint8_t *rgb, uint32_t rgb_stride,
YCbCrType yuv_type);
void yuv422_rgb24_sseu(
uint32_t width, uint32_t height,
const uint8_t *y, const uint8_t *u, const uint8_t *v, uint32_t y_stride, uint32_t uv_stride,
uint8_t *rgb, uint32_t rgb_stride,
YCbCrType yuv_type);
void yuv422_rgba_sseu(
uint32_t width, uint32_t height,
const uint8_t *y, const uint8_t *u, const uint8_t *v, uint32_t y_stride, uint32_t uv_stride,
uint8_t *rgb, uint32_t rgb_stride,
YCbCrType yuv_type);
void yuv422_bgra_sseu(
uint32_t width, uint32_t height,
const uint8_t *y, const uint8_t *u, const uint8_t *v, uint32_t y_stride, uint32_t uv_stride,
uint8_t *rgb, uint32_t rgb_stride,
YCbCrType yuv_type);
void yuv422_argb_sseu(
uint32_t width, uint32_t height,
const uint8_t *y, const uint8_t *u, const uint8_t *v, uint32_t y_stride, uint32_t uv_stride,
uint8_t *rgb, uint32_t rgb_stride,
YCbCrType yuv_type);
void yuv422_abgr_sseu(
uint32_t width, uint32_t height,
const uint8_t *y, const uint8_t *u, const uint8_t *v, uint32_t y_stride, uint32_t uv_stride,
uint8_t *rgb, uint32_t rgb_stride,
YCbCrType yuv_type);
void yuvnv12_rgb565_sseu(
uint32_t width, uint32_t height,
const uint8_t *y, const uint8_t *u, const uint8_t *v, uint32_t y_stride, uint32_t uv_stride,
uint8_t *rgb, uint32_t rgb_stride,
YCbCrType yuv_type);
void yuvnv12_rgb24_sseu(
uint32_t width, uint32_t height,
const uint8_t *y, const uint8_t *u, const uint8_t *v, uint32_t y_stride, uint32_t uv_stride,
uint8_t *rgb, uint32_t rgb_stride,
YCbCrType yuv_type);
void yuvnv12_rgba_sseu(
uint32_t width, uint32_t height,
const uint8_t *y, const uint8_t *u, const uint8_t *v, uint32_t y_stride, uint32_t uv_stride,
uint8_t *rgb, uint32_t rgb_stride,
YCbCrType yuv_type);
void yuvnv12_bgra_sseu(
uint32_t width, uint32_t height,
const uint8_t *y, const uint8_t *u, const uint8_t *v, uint32_t y_stride, uint32_t uv_stride,
uint8_t *rgb, uint32_t rgb_stride,
YCbCrType yuv_type);
void yuvnv12_argb_sseu(
uint32_t width, uint32_t height,
const uint8_t *y, const uint8_t *u, const uint8_t *v, uint32_t y_stride, uint32_t uv_stride,
uint8_t *rgb, uint32_t rgb_stride,
YCbCrType yuv_type);
void yuvnv12_abgr_sseu(
uint32_t width, uint32_t height,
const uint8_t *y, const uint8_t *u, const uint8_t *v, uint32_t y_stride, uint32_t uv_stride,
uint8_t *rgb, uint32_t rgb_stride,
YCbCrType yuv_type);
// rgb to yuv, standard c implementation
void rgb24_yuv420_std(
uint32_t width, uint32_t height,
const uint8_t *rgb, uint32_t rgb_stride,
uint8_t *y, uint8_t *u, uint8_t *v, uint32_t y_stride, uint32_t uv_stride,
YCbCrType yuv_type);
// rgb to yuv, sse implementation
// pointers must be 16 byte aligned, and strides must be divisible by 16
void rgb24_yuv420_sse(
uint32_t width, uint32_t height,
const uint8_t *rgb, uint32_t rgb_stride,
uint8_t *y, uint8_t *u, uint8_t *v, uint32_t y_stride, uint32_t uv_stride,
YCbCrType yuv_type);
// rgb to yuv, sse implementation
// pointers do not need to be 16 byte aligned
void rgb24_yuv420_sseu(
uint32_t width, uint32_t height,
const uint8_t *rgb, uint32_t rgb_stride,
uint8_t *y, uint8_t *u, uint8_t *v, uint32_t y_stride, uint32_t uv_stride,
YCbCrType yuv_type);