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
|
/*
* Copyright (c) 2020 Björn Ottosson
* Copyright (c) 2022 Clément Bœsch <u pkh me>
*
* This file is part of FFmpeg.
*
* FFmpeg is free software; you can redistribute it and/or
* modify it under the terms of the GNU Lesser General Public
* License as published by the Free Software Foundation; either
* version 2.1 of the License, or (at your option) any later version.
*
* FFmpeg is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
* Lesser General Public License for more details.
*
* You should have received a copy of the GNU Lesser General Public
* License along with FFmpeg; if not, write to the Free Software
* Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
*/
#include "libavutil/common.h"
#include "palette.h"
#define K ((1 << 16) - 1)
#define K2 ((int64_t)K*K)
#define P ((1 << 9) - 1)
/**
* Table mapping formula:
* f(x) = x < 0.04045 ? x/12.92 : ((x+0.055)/1.055)^2.4 (sRGB EOTF)
* Where x is the normalized index in the table and f(x) the value in the table.
* f(x) is remapped to [0;K] and rounded.
*/
static const uint16_t srgb2linear[256] = {
0x0000, 0x0014, 0x0028, 0x003c, 0x0050, 0x0063, 0x0077, 0x008b,
0x009f, 0x00b3, 0x00c7, 0x00db, 0x00f1, 0x0108, 0x0120, 0x0139,
0x0154, 0x016f, 0x018c, 0x01ab, 0x01ca, 0x01eb, 0x020e, 0x0232,
0x0257, 0x027d, 0x02a5, 0x02ce, 0x02f9, 0x0325, 0x0353, 0x0382,
0x03b3, 0x03e5, 0x0418, 0x044d, 0x0484, 0x04bc, 0x04f6, 0x0532,
0x056f, 0x05ad, 0x05ed, 0x062f, 0x0673, 0x06b8, 0x06fe, 0x0747,
0x0791, 0x07dd, 0x082a, 0x087a, 0x08ca, 0x091d, 0x0972, 0x09c8,
0x0a20, 0x0a79, 0x0ad5, 0x0b32, 0x0b91, 0x0bf2, 0x0c55, 0x0cba,
0x0d20, 0x0d88, 0x0df2, 0x0e5e, 0x0ecc, 0x0f3c, 0x0fae, 0x1021,
0x1097, 0x110e, 0x1188, 0x1203, 0x1280, 0x1300, 0x1381, 0x1404,
0x1489, 0x1510, 0x159a, 0x1625, 0x16b2, 0x1741, 0x17d3, 0x1866,
0x18fb, 0x1993, 0x1a2c, 0x1ac8, 0x1b66, 0x1c06, 0x1ca7, 0x1d4c,
0x1df2, 0x1e9a, 0x1f44, 0x1ff1, 0x20a0, 0x2150, 0x2204, 0x22b9,
0x2370, 0x242a, 0x24e5, 0x25a3, 0x2664, 0x2726, 0x27eb, 0x28b1,
0x297b, 0x2a46, 0x2b14, 0x2be3, 0x2cb6, 0x2d8a, 0x2e61, 0x2f3a,
0x3015, 0x30f2, 0x31d2, 0x32b4, 0x3399, 0x3480, 0x3569, 0x3655,
0x3742, 0x3833, 0x3925, 0x3a1a, 0x3b12, 0x3c0b, 0x3d07, 0x3e06,
0x3f07, 0x400a, 0x4110, 0x4218, 0x4323, 0x4430, 0x453f, 0x4651,
0x4765, 0x487c, 0x4995, 0x4ab1, 0x4bcf, 0x4cf0, 0x4e13, 0x4f39,
0x5061, 0x518c, 0x52b9, 0x53e9, 0x551b, 0x5650, 0x5787, 0x58c1,
0x59fe, 0x5b3d, 0x5c7e, 0x5dc2, 0x5f09, 0x6052, 0x619e, 0x62ed,
0x643e, 0x6591, 0x66e8, 0x6840, 0x699c, 0x6afa, 0x6c5b, 0x6dbe,
0x6f24, 0x708d, 0x71f8, 0x7366, 0x74d7, 0x764a, 0x77c0, 0x7939,
0x7ab4, 0x7c32, 0x7db3, 0x7f37, 0x80bd, 0x8246, 0x83d1, 0x855f,
0x86f0, 0x8884, 0x8a1b, 0x8bb4, 0x8d50, 0x8eef, 0x9090, 0x9235,
0x93dc, 0x9586, 0x9732, 0x98e2, 0x9a94, 0x9c49, 0x9e01, 0x9fbb,
0xa179, 0xa339, 0xa4fc, 0xa6c2, 0xa88b, 0xaa56, 0xac25, 0xadf6,
0xafca, 0xb1a1, 0xb37b, 0xb557, 0xb737, 0xb919, 0xbaff, 0xbce7,
0xbed2, 0xc0c0, 0xc2b1, 0xc4a5, 0xc69c, 0xc895, 0xca92, 0xcc91,
0xce94, 0xd099, 0xd2a1, 0xd4ad, 0xd6bb, 0xd8cc, 0xdae0, 0xdcf7,
0xdf11, 0xe12e, 0xe34e, 0xe571, 0xe797, 0xe9c0, 0xebec, 0xee1b,
0xf04d, 0xf282, 0xf4ba, 0xf6f5, 0xf933, 0xfb74, 0xfdb8, 0xffff,
};
/**
* Table mapping formula:
* f(x) = x < 0.0031308 ? x*12.92 : 1.055*x^(1/2.4)-0.055 (sRGB OETF)
* Where x is the normalized index in the table and f(x) the value in the table.
* f(x) is remapped to [0;0xff] and rounded.
*
* Since a 16-bit table is too large, we reduce its precision to 9-bit.
*/
static const uint8_t linear2srgb[P + 1] = {
0x00, 0x06, 0x0d, 0x12, 0x16, 0x19, 0x1c, 0x1f, 0x22, 0x24, 0x26, 0x28, 0x2a, 0x2c, 0x2e, 0x30,
0x32, 0x33, 0x35, 0x36, 0x38, 0x39, 0x3b, 0x3c, 0x3d, 0x3e, 0x40, 0x41, 0x42, 0x43, 0x45, 0x46,
0x47, 0x48, 0x49, 0x4a, 0x4b, 0x4c, 0x4d, 0x4e, 0x4f, 0x50, 0x51, 0x52, 0x53, 0x54, 0x55, 0x56,
0x56, 0x57, 0x58, 0x59, 0x5a, 0x5b, 0x5b, 0x5c, 0x5d, 0x5e, 0x5f, 0x5f, 0x60, 0x61, 0x62, 0x62,
0x63, 0x64, 0x65, 0x65, 0x66, 0x67, 0x67, 0x68, 0x69, 0x6a, 0x6a, 0x6b, 0x6c, 0x6c, 0x6d, 0x6e,
0x6e, 0x6f, 0x6f, 0x70, 0x71, 0x71, 0x72, 0x73, 0x73, 0x74, 0x74, 0x75, 0x76, 0x76, 0x77, 0x77,
0x78, 0x79, 0x79, 0x7a, 0x7a, 0x7b, 0x7b, 0x7c, 0x7d, 0x7d, 0x7e, 0x7e, 0x7f, 0x7f, 0x80, 0x80,
0x81, 0x81, 0x82, 0x82, 0x83, 0x84, 0x84, 0x85, 0x85, 0x86, 0x86, 0x87, 0x87, 0x88, 0x88, 0x89,
0x89, 0x8a, 0x8a, 0x8b, 0x8b, 0x8c, 0x8c, 0x8c, 0x8d, 0x8d, 0x8e, 0x8e, 0x8f, 0x8f, 0x90, 0x90,
0x91, 0x91, 0x92, 0x92, 0x93, 0x93, 0x93, 0x94, 0x94, 0x95, 0x95, 0x96, 0x96, 0x97, 0x97, 0x97,
0x98, 0x98, 0x99, 0x99, 0x9a, 0x9a, 0x9a, 0x9b, 0x9b, 0x9c, 0x9c, 0x9c, 0x9d, 0x9d, 0x9e, 0x9e,
0x9f, 0x9f, 0x9f, 0xa0, 0xa0, 0xa1, 0xa1, 0xa1, 0xa2, 0xa2, 0xa3, 0xa3, 0xa3, 0xa4, 0xa4, 0xa5,
0xa5, 0xa5, 0xa6, 0xa6, 0xa6, 0xa7, 0xa7, 0xa8, 0xa8, 0xa8, 0xa9, 0xa9, 0xa9, 0xaa, 0xaa, 0xab,
0xab, 0xab, 0xac, 0xac, 0xac, 0xad, 0xad, 0xae, 0xae, 0xae, 0xaf, 0xaf, 0xaf, 0xb0, 0xb0, 0xb0,
0xb1, 0xb1, 0xb1, 0xb2, 0xb2, 0xb3, 0xb3, 0xb3, 0xb4, 0xb4, 0xb4, 0xb5, 0xb5, 0xb5, 0xb6, 0xb6,
0xb6, 0xb7, 0xb7, 0xb7, 0xb8, 0xb8, 0xb8, 0xb9, 0xb9, 0xb9, 0xba, 0xba, 0xba, 0xbb, 0xbb, 0xbb,
0xbc, 0xbc, 0xbc, 0xbd, 0xbd, 0xbd, 0xbe, 0xbe, 0xbe, 0xbf, 0xbf, 0xbf, 0xc0, 0xc0, 0xc0, 0xc1,
0xc1, 0xc1, 0xc1, 0xc2, 0xc2, 0xc2, 0xc3, 0xc3, 0xc3, 0xc4, 0xc4, 0xc4, 0xc5, 0xc5, 0xc5, 0xc6,
0xc6, 0xc6, 0xc6, 0xc7, 0xc7, 0xc7, 0xc8, 0xc8, 0xc8, 0xc9, 0xc9, 0xc9, 0xc9, 0xca, 0xca, 0xca,
0xcb, 0xcb, 0xcb, 0xcc, 0xcc, 0xcc, 0xcc, 0xcd, 0xcd, 0xcd, 0xce, 0xce, 0xce, 0xce, 0xcf, 0xcf,
0xcf, 0xd0, 0xd0, 0xd0, 0xd0, 0xd1, 0xd1, 0xd1, 0xd2, 0xd2, 0xd2, 0xd2, 0xd3, 0xd3, 0xd3, 0xd4,
0xd4, 0xd4, 0xd4, 0xd5, 0xd5, 0xd5, 0xd6, 0xd6, 0xd6, 0xd6, 0xd7, 0xd7, 0xd7, 0xd7, 0xd8, 0xd8,
0xd8, 0xd9, 0xd9, 0xd9, 0xd9, 0xda, 0xda, 0xda, 0xda, 0xdb, 0xdb, 0xdb, 0xdc, 0xdc, 0xdc, 0xdc,
0xdd, 0xdd, 0xdd, 0xdd, 0xde, 0xde, 0xde, 0xde, 0xdf, 0xdf, 0xdf, 0xe0, 0xe0, 0xe0, 0xe0, 0xe1,
0xe1, 0xe1, 0xe1, 0xe2, 0xe2, 0xe2, 0xe2, 0xe3, 0xe3, 0xe3, 0xe3, 0xe4, 0xe4, 0xe4, 0xe4, 0xe5,
0xe5, 0xe5, 0xe5, 0xe6, 0xe6, 0xe6, 0xe6, 0xe7, 0xe7, 0xe7, 0xe7, 0xe8, 0xe8, 0xe8, 0xe8, 0xe9,
0xe9, 0xe9, 0xe9, 0xea, 0xea, 0xea, 0xea, 0xeb, 0xeb, 0xeb, 0xeb, 0xec, 0xec, 0xec, 0xec, 0xed,
0xed, 0xed, 0xed, 0xee, 0xee, 0xee, 0xee, 0xef, 0xef, 0xef, 0xef, 0xef, 0xf0, 0xf0, 0xf0, 0xf0,
0xf1, 0xf1, 0xf1, 0xf1, 0xf2, 0xf2, 0xf2, 0xf2, 0xf3, 0xf3, 0xf3, 0xf3, 0xf3, 0xf4, 0xf4, 0xf4,
0xf4, 0xf5, 0xf5, 0xf5, 0xf5, 0xf6, 0xf6, 0xf6, 0xf6, 0xf6, 0xf7, 0xf7, 0xf7, 0xf7, 0xf8, 0xf8,
0xf8, 0xf8, 0xf9, 0xf9, 0xf9, 0xf9, 0xf9, 0xfa, 0xfa, 0xfa, 0xfa, 0xfb, 0xfb, 0xfb, 0xfb, 0xfb,
0xfc, 0xfc, 0xfc, 0xfc, 0xfd, 0xfd, 0xfd, 0xfd, 0xfd, 0xfe, 0xfe, 0xfe, 0xfe, 0xff, 0xff, 0xff,
};
int32_t ff_srgb_u8_to_linear_int(uint8_t x)
{
return (int32_t)srgb2linear[x];
}
uint8_t ff_linear_int_to_srgb_u8(int32_t x)
{
if (x <= 0) {
return 0;
} else if (x >= K) {
return 0xff;
} else {
const int32_t xP = x * P;
const int32_t i = xP / K;
const int32_t m = xP % K;
const int32_t y0 = linear2srgb[i];
const int32_t y1 = linear2srgb[i + 1];
return (m * (y1 - y0) + K/2) / K + y0;
}
}
/* Integer cube root, working only within [0;1] */
static int32_t cbrt01_int(int32_t x)
{
int64_t u;
/* Approximation curve is for the [0;1] range */
if (x <= 0) return 0;
if (x >= K) return K;
/*
* Initial approximation: x³ - 2.19893x² + 2.01593x + 0.219407
*
* We are not using any rounding here since the precision is not important
* at this stage and it would require the more expensive rounding function
* that deals with negative numbers.
*/
u = x*(x*(x + -144107LL) / K + 132114LL) / K + 14379LL;
/*
* Refine with 2 Halley iterations:
* uₙ₊₁ = uₙ-2f(uₙ)f'(uₙ)/(2f'(uₙ)²-f(uₙ)f"(uₙ))
* = uₙ(2x+uₙ³)/(x+2uₙ³)
*
* Note: u is not expected to be < 0, so we can use the (a+b/2)/b rounding.
*/
for (int i = 0; i < 2; i++) {
const int64_t u3 = u*u*u;
const int64_t den = x + (2*u3 + K2/2) / K2;
u = (u * (2*x + (u3 + K2/2) / K2) + den/2) / den;
}
return u;
}
static int64_t div_round64(int64_t a, int64_t b) { return (a^b)<0 ? (a-b/2)/b : (a+b/2)/b; }
struct Lab ff_srgb_u8_to_oklab_int(uint32_t srgb)
{
const int32_t r = (int32_t)srgb2linear[srgb >> 16 & 0xff];
const int32_t g = (int32_t)srgb2linear[srgb >> 8 & 0xff];
const int32_t b = (int32_t)srgb2linear[srgb & 0xff];
// Note: lms can actually be slightly over K due to rounded coefficients
const int32_t l = (27015LL*r + 35149LL*g + 3372LL*b + K/2) / K;
const int32_t m = (13887LL*r + 44610LL*g + 7038LL*b + K/2) / K;
const int32_t s = ( 5787LL*r + 18462LL*g + 41286LL*b + K/2) / K;
const int32_t l_ = cbrt01_int(l);
const int32_t m_ = cbrt01_int(m);
const int32_t s_ = cbrt01_int(s);
const struct Lab ret = {
.L = div_round64( 13792LL*l_ + 52010LL*m_ - 267LL*s_, K),
.a = div_round64(129628LL*l_ - 159158LL*m_ + 29530LL*s_, K),
.b = div_round64( 1698LL*l_ + 51299LL*m_ - 52997LL*s_, K),
};
return ret;
}
uint32_t ff_oklab_int_to_srgb_u8(struct Lab c)
{
const int64_t l_ = c.L + div_round64(25974LL * c.a, K) + div_round64(14143LL * c.b, K);
const int64_t m_ = c.L + div_round64(-6918LL * c.a, K) + div_round64(-4185LL * c.b, K);
const int64_t s_ = c.L + div_round64(-5864LL * c.a, K) + div_round64(-84638LL * c.b, K);
const int32_t l = l_*l_*l_ / K2;
const int32_t m = m_*m_*m_ / K2;
const int32_t s = s_*s_*s_ / K2;
const uint8_t r = ff_linear_int_to_srgb_u8((267169LL * l + -216771LL * m + 15137LL * s + K/2) / K);
const uint8_t g = ff_linear_int_to_srgb_u8((-83127LL * l + 171030LL * m + -22368LL * s + K/2) / K);
const uint8_t b = ff_linear_int_to_srgb_u8((-275LL * l + -46099LL * m + 111909LL * s + K/2) / K);
return r<<16 | g<<8 | b;
}
uint32_t ff_lowbias32(uint32_t x)
{
x ^= x >> 16;
x *= 0x7feb352d;
x ^= x >> 15;
x *= 0x846ca68b;
x ^= x >> 16;
return x;
}
|
