FFmpeg
vc1dsp.h
Go to the documentation of this file.
1 /*
2  * VC-1 and WMV3 decoder - DSP functions
3  * Copyright (c) 2006 Konstantin Shishkov
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 /**
23  * @file
24  * VC-1 and WMV3 decoder
25  */
26 
27 #ifndef AVCODEC_VC1DSP_H
28 #define AVCODEC_VC1DSP_H
29 
30 #include "hpeldsp.h"
31 #include "h264chroma.h"
32 
33 typedef void (*vc1op_pixels_func)(uint8_t *block/*align width (8 or 16)*/, const uint8_t *pixels/*align 1*/, ptrdiff_t line_size, int h);
34 
35 typedef struct VC1DSPContext {
36  /* vc1 functions */
37  void (*vc1_inv_trans_8x8)(int16_t *b);
38  void (*vc1_inv_trans_8x4)(uint8_t *dest, ptrdiff_t stride, int16_t *block);
39  void (*vc1_inv_trans_4x8)(uint8_t *dest, ptrdiff_t stride, int16_t *block);
40  void (*vc1_inv_trans_4x4)(uint8_t *dest, ptrdiff_t stride, int16_t *block);
41  void (*vc1_inv_trans_8x8_dc)(uint8_t *dest, ptrdiff_t stride, int16_t *block);
42  void (*vc1_inv_trans_8x4_dc)(uint8_t *dest, ptrdiff_t stride, int16_t *block);
43  void (*vc1_inv_trans_4x8_dc)(uint8_t *dest, ptrdiff_t stride, int16_t *block);
44  void (*vc1_inv_trans_4x4_dc)(uint8_t *dest, ptrdiff_t stride, int16_t *block);
45  void (*vc1_v_overlap)(uint8_t *src, ptrdiff_t stride);
46  void (*vc1_h_overlap)(uint8_t *src, ptrdiff_t stride);
47  void (*vc1_v_s_overlap)(int16_t *top, int16_t *bottom);
48  void (*vc1_h_s_overlap)(int16_t *left, int16_t *right, ptrdiff_t left_stride, ptrdiff_t right_stride, int flags);
49  void (*vc1_v_loop_filter4)(uint8_t *src, ptrdiff_t stride, int pq);
50  void (*vc1_h_loop_filter4)(uint8_t *src, ptrdiff_t stride, int pq);
51  void (*vc1_v_loop_filter8)(uint8_t *src, ptrdiff_t stride, int pq);
52  void (*vc1_h_loop_filter8)(uint8_t *src, ptrdiff_t stride, int pq);
53  void (*vc1_v_loop_filter16)(uint8_t *src, ptrdiff_t stride, int pq);
54  void (*vc1_h_loop_filter16)(uint8_t *src, ptrdiff_t stride, int pq);
55 
56  /* put 8x8 block with bicubic interpolation and quarterpel precision
57  * last argument is actually round value instead of height
58  */
61 
62  /* This is really one func used in VC-1 decoding */
65 
66  /* Windows Media Image functions */
67  void (*sprite_h)(uint8_t *dst, const uint8_t *src, int offset, int advance, int count);
68  void (*sprite_v_single)(uint8_t *dst, const uint8_t *src1a, const uint8_t *src1b, int offset, int width);
69  void (*sprite_v_double_noscale)(uint8_t *dst, const uint8_t *src1a, const uint8_t *src2a, int alpha, int width);
70  void (*sprite_v_double_onescale)(uint8_t *dst, const uint8_t *src1a, const uint8_t *src1b, int offset1,
71  const uint8_t *src2a, int alpha, int width);
72  void (*sprite_v_double_twoscale)(uint8_t *dst, const uint8_t *src1a, const uint8_t *src1b, int offset1,
73  const uint8_t *src2a, const uint8_t *src2b, int offset2,
74  int alpha, int width);
75 
76  /**
77  * Search buf from the start for up to size bytes. Return the index
78  * of a zero byte, or >= size if not found. Ideally, use lookahead
79  * to filter out any zero bytes that are known to not be followed by
80  * one or more further zero bytes and a one byte.
81  */
82  int (*startcode_find_candidate)(const uint8_t *buf, int size);
83 
84  /* Copy a buffer, removing startcode emulation escape bytes as we go */
85  int (*vc1_unescape_buffer)(const uint8_t *src, int size, uint8_t *dst);
87 
96 
97 #endif /* AVCODEC_VC1DSP_H */
VC1DSPContext::sprite_v_double_noscale
void(* sprite_v_double_noscale)(uint8_t *dst, const uint8_t *src1a, const uint8_t *src2a, int alpha, int width)
Definition: vc1dsp.h:69
h264_chroma_mc_func
void(* h264_chroma_mc_func)(uint8_t *dst, const uint8_t *src, ptrdiff_t srcStride, int h, int x, int y)
Definition: h264chroma.h:25
ff_vc1dsp_init_aarch64
void ff_vc1dsp_init_aarch64(VC1DSPContext *dsp)
Definition: vc1dsp_init_aarch64.c:113
VC1DSPContext::vc1_v_loop_filter16
void(* vc1_v_loop_filter16)(uint8_t *src, ptrdiff_t stride, int pq)
Definition: vc1dsp.h:53
VC1DSPContext::vc1_inv_trans_4x4
void(* vc1_inv_trans_4x4)(uint8_t *dest, ptrdiff_t stride, int16_t *block)
Definition: vc1dsp.h:40
VC1DSPContext::avg_vc1_mspel_pixels_tab
vc1op_pixels_func avg_vc1_mspel_pixels_tab[2][16]
Definition: vc1dsp.h:60
VC1DSPContext::avg_no_rnd_vc1_chroma_pixels_tab
h264_chroma_mc_func avg_no_rnd_vc1_chroma_pixels_tab[3]
Definition: vc1dsp.h:64
b
#define b
Definition: input.c:41
ff_vc1dsp_init_mips
void ff_vc1dsp_init_mips(VC1DSPContext *dsp)
Definition: vc1dsp_init_mips.c:31
VC1DSPContext::vc1_inv_trans_8x8_dc
void(* vc1_inv_trans_8x8_dc)(uint8_t *dest, ptrdiff_t stride, int16_t *block)
Definition: vc1dsp.h:41
VC1DSPContext::put_no_rnd_vc1_chroma_pixels_tab
h264_chroma_mc_func put_no_rnd_vc1_chroma_pixels_tab[3]
Definition: vc1dsp.h:63
VC1DSPContext::vc1_inv_trans_4x4_dc
void(* vc1_inv_trans_4x4_dc)(uint8_t *dest, ptrdiff_t stride, int16_t *block)
Definition: vc1dsp.h:44
VC1DSPContext::vc1_h_overlap
void(* vc1_h_overlap)(uint8_t *src, ptrdiff_t stride)
Definition: vc1dsp.h:46
VC1DSPContext::vc1_v_loop_filter4
void(* vc1_v_loop_filter4)(uint8_t *src, ptrdiff_t stride, int pq)
Definition: vc1dsp.h:49
VC1DSPContext::vc1_h_loop_filter4
void(* vc1_h_loop_filter4)(uint8_t *src, ptrdiff_t stride, int pq)
Definition: vc1dsp.h:50
VC1DSPContext::vc1_inv_trans_8x4_dc
void(* vc1_inv_trans_8x4_dc)(uint8_t *dest, ptrdiff_t stride, int16_t *block)
Definition: vc1dsp.h:42
VC1DSPContext::sprite_v_double_twoscale
void(* sprite_v_double_twoscale)(uint8_t *dst, const uint8_t *src1a, const uint8_t *src1b, int offset1, const uint8_t *src2a, const uint8_t *src2b, int offset2, int alpha, int width)
Definition: vc1dsp.h:72
VC1DSPContext::vc1_h_loop_filter16
void(* vc1_h_loop_filter16)(uint8_t *src, ptrdiff_t stride, int pq)
Definition: vc1dsp.h:54
width
#define width
VC1DSPContext::sprite_h
void(* sprite_h)(uint8_t *dst, const uint8_t *src, int offset, int advance, int count)
Definition: vc1dsp.h:67
VC1DSPContext::vc1_v_overlap
void(* vc1_v_overlap)(uint8_t *src, ptrdiff_t stride)
Definition: vc1dsp.h:45
ff_vc1dsp_init
void ff_vc1dsp_init(VC1DSPContext *c)
Definition: vc1dsp.c:974
vc1op_pixels_func
void(* vc1op_pixels_func)(uint8_t *block, const uint8_t *pixels, ptrdiff_t line_size, int h)
Definition: vc1dsp.h:33
VC1DSPContext::vc1_inv_trans_8x4
void(* vc1_inv_trans_8x4)(uint8_t *dest, ptrdiff_t stride, int16_t *block)
Definition: vc1dsp.h:38
VC1DSPContext::vc1_inv_trans_4x8_dc
void(* vc1_inv_trans_4x8_dc)(uint8_t *dest, ptrdiff_t stride, int16_t *block)
Definition: vc1dsp.h:43
c
Undefined Behavior In the C some operations are like signed integer dereferencing freed accessing outside allocated Undefined Behavior must not occur in a C it is not safe even if the output of undefined operations is unused The unsafety may seem nit picking but Optimizing compilers have in fact optimized code on the assumption that no undefined Behavior occurs Optimizing code based on wrong assumptions can and has in some cases lead to effects beyond the output of computations The signed integer overflow problem in speed critical code Code which is highly optimized and works with signed integers sometimes has the problem that often the output of the computation does not c
Definition: undefined.txt:32
ff_vc1dsp_init_arm
void ff_vc1dsp_init_arm(VC1DSPContext *dsp)
Definition: vc1dsp_init_arm.c:27
ff_vc1dsp_init_x86
void ff_vc1dsp_init_x86(VC1DSPContext *dsp)
Definition: vc1dsp_init.c:101
size
int size
Definition: twinvq_data.h:10344
ff_vc1dsp_init_ppc
void ff_vc1dsp_init_ppc(VC1DSPContext *c)
Definition: vc1dsp_altivec.c:354
h264chroma.h
ff_vc1dsp_init_riscv
void ff_vc1dsp_init_riscv(VC1DSPContext *c)
Definition: vc1dsp_init.c:33
offset
it s the only field you need to keep assuming you have a context There is some magic you don t need to care about around this just let it vf offset
Definition: writing_filters.txt:86
VC1DSPContext::sprite_v_single
void(* sprite_v_single)(uint8_t *dst, const uint8_t *src1a, const uint8_t *src1b, int offset, int width)
Definition: vc1dsp.h:68
VC1DSPContext::vc1_inv_trans_8x8
void(* vc1_inv_trans_8x8)(int16_t *b)
Definition: vc1dsp.h:37
VC1DSPContext::startcode_find_candidate
int(* startcode_find_candidate)(const uint8_t *buf, int size)
Search buf from the start for up to size bytes.
Definition: vc1dsp.h:82
VC1DSPContext::sprite_v_double_onescale
void(* sprite_v_double_onescale)(uint8_t *dst, const uint8_t *src1a, const uint8_t *src1b, int offset1, const uint8_t *src2a, int alpha, int width)
Definition: vc1dsp.h:70
VC1DSPContext::vc1_unescape_buffer
int(* vc1_unescape_buffer)(const uint8_t *src, int size, uint8_t *dst)
Definition: vc1dsp.h:85
stride
#define stride
Definition: h264pred_template.c:537
VC1DSPContext
Definition: vc1dsp.h:35
VC1DSPContext::vc1_h_loop_filter8
void(* vc1_h_loop_filter8)(uint8_t *src, ptrdiff_t stride, int pq)
Definition: vc1dsp.h:52
VC1DSPContext::put_vc1_mspel_pixels_tab
vc1op_pixels_func put_vc1_mspel_pixels_tab[2][16]
Definition: vc1dsp.h:59
left
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 left
Definition: snow.txt:386
VC1DSPContext::vc1_v_loop_filter8
void(* vc1_v_loop_filter8)(uint8_t *src, ptrdiff_t stride, int pq)
Definition: vc1dsp.h:51
ff_vc1dsp_init_loongarch
void ff_vc1dsp_init_loongarch(VC1DSPContext *dsp)
Definition: vc1dsp_init_loongarch.c:37
alpha
static const int16_t alpha[]
Definition: ilbcdata.h:55
src
INIT_CLIP pixel * src
Definition: h264pred_template.c:418
hpeldsp.h
flags
#define flags(name, subs,...)
Definition: cbs_av1.c:474
block
The exact code depends on how similar the blocks are and how related they are to the block
Definition: filter_design.txt:207
h
h
Definition: vp9dsp_template.c:2038
VC1DSPContext::vc1_inv_trans_4x8
void(* vc1_inv_trans_4x8)(uint8_t *dest, ptrdiff_t stride, int16_t *block)
Definition: vc1dsp.h:39
int
int
Definition: ffmpeg_filter.c:409
VC1DSPContext::vc1_v_s_overlap
void(* vc1_v_s_overlap)(int16_t *top, int16_t *bottom)
Definition: vc1dsp.h:47
VC1DSPContext::vc1_h_s_overlap
void(* vc1_h_s_overlap)(int16_t *left, int16_t *right, ptrdiff_t left_stride, ptrdiff_t right_stride, int flags)
Definition: vc1dsp.h:48