FFmpeg
vble.c
Go to the documentation of this file.
1 /*
2  * VBLE Decoder
3  * Copyright (c) 2011 Derek Buitenhuis
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  * VBLE Decoder
25  */
26 
27 #include "libavutil/imgutils.h"
28 
29 #define BITSTREAM_READER_LE
30 #include "avcodec.h"
31 #include "codec_internal.h"
32 #include "get_bits.h"
33 #include "lossless_videodsp.h"
34 #include "mathops.h"
35 #include "thread.h"
36 
37 typedef struct VBLEContext {
40 
41  int size;
42  uint8_t *val; ///< This array first holds the lengths of vlc symbols and then their value.
43 } VBLEContext;
44 
46 {
47  int i;
48  int allbits = 0;
49  static const uint8_t LUT[256] = {
50  8,0,1,0,2,0,1,0,3,0,1,0,2,0,1,0,4,0,1,0,2,0,1,0,3,0,1,0,2,0,1,0,
51  5,0,1,0,2,0,1,0,3,0,1,0,2,0,1,0,4,0,1,0,2,0,1,0,3,0,1,0,2,0,1,0,
52  6,0,1,0,2,0,1,0,3,0,1,0,2,0,1,0,4,0,1,0,2,0,1,0,3,0,1,0,2,0,1,0,
53  5,0,1,0,2,0,1,0,3,0,1,0,2,0,1,0,4,0,1,0,2,0,1,0,3,0,1,0,2,0,1,0,
54  7,0,1,0,2,0,1,0,3,0,1,0,2,0,1,0,4,0,1,0,2,0,1,0,3,0,1,0,2,0,1,0,
55  5,0,1,0,2,0,1,0,3,0,1,0,2,0,1,0,4,0,1,0,2,0,1,0,3,0,1,0,2,0,1,0,
56  6,0,1,0,2,0,1,0,3,0,1,0,2,0,1,0,4,0,1,0,2,0,1,0,3,0,1,0,2,0,1,0,
57  5,0,1,0,2,0,1,0,3,0,1,0,2,0,1,0,4,0,1,0,2,0,1,0,3,0,1,0,2,0,1,0,
58  };
59 
60  /* Read all the lengths in first */
61  for (i = 0; i < ctx->size; i++) {
62  /* At most we need to read 9 bits total to get indices up to 8 */
63  int val = show_bits(gb, 8);
64 
65  // read reverse unary
66  if (val) {
67  val = LUT[val];
68  skip_bits(gb, val + 1);
69  ctx->val[i] = val;
70  } else {
71  skip_bits(gb, 8);
72  if (!get_bits1(gb))
73  return -1;
74  ctx->val[i] = 8;
75  }
76  allbits += ctx->val[i];
77  }
78 
79  /* Check we have enough bits left */
80  if (get_bits_left(gb) < allbits)
81  return -1;
82  return 0;
83 }
84 
86  GetBitContext *gb, int plane,
87  int offset, int width, int height)
88 {
89  uint8_t *dst = pic->data[plane];
90  uint8_t *val = ctx->val + offset;
91  int stride = pic->linesize[plane];
92  int i, j, left, left_top;
93 
94  for (i = 0; i < height; i++) {
95  for (j = 0; j < width; j++) {
96  /* get_bits can't take a length of 0 */
97  if (val[j]) {
98  int v = (1 << val[j]) + get_bits(gb, val[j]) - 1;
99  val[j] = (v >> 1) ^ -(v & 1);
100  }
101  }
102  if (i) {
103  left = 0;
104  left_top = dst[-stride];
105  ctx->llviddsp.add_median_pred(dst, dst - stride, val,
106  width, &left, &left_top);
107  } else {
108  dst[0] = val[0];
109  for (j = 1; j < width; j++)
110  dst[j] = val[j] + dst[j - 1];
111  }
112  dst += stride;
113  val += width;
114  }
115 }
116 
117 static int vble_decode_frame(AVCodecContext *avctx, AVFrame *pic,
118  int *got_frame, AVPacket *avpkt)
119 {
120  VBLEContext *ctx = avctx->priv_data;
121  GetBitContext gb;
122  const uint8_t *src = avpkt->data;
123  int version;
124  int offset = 0;
125  int width_uv = avctx->width / 2, height_uv = avctx->height / 2;
126  int ret;
127 
128  if (avpkt->size < 4 || avpkt->size - 4 > INT_MAX/8) {
129  av_log(avctx, AV_LOG_ERROR, "Invalid packet size\n");
130  return AVERROR_INVALIDDATA;
131  }
132 
133  /* Allocate buffer */
134  if ((ret = ff_thread_get_buffer(avctx, pic, 0)) < 0)
135  return ret;
136 
137  /* Set flags */
138  pic->flags |= AV_FRAME_FLAG_KEY;
140 
141  /* Version should always be 1 */
142  version = AV_RL32(src);
143 
144  if (version != 1)
145  av_log(avctx, AV_LOG_WARNING, "Unsupported VBLE Version: %d\n", version);
146 
147  init_get_bits(&gb, src + 4, (avpkt->size - 4) * 8);
148 
149  /* Unpack */
150  if (vble_unpack(ctx, &gb) < 0) {
151  av_log(avctx, AV_LOG_ERROR, "Invalid Code\n");
152  return AVERROR_INVALIDDATA;
153  }
154 
155  /* Restore planes. Should be almost identical to Huffyuv's. */
156  vble_restore_plane(ctx, pic, &gb, 0, offset, avctx->width, avctx->height);
157 
158  /* Chroma */
159  if (!(ctx->avctx->flags & AV_CODEC_FLAG_GRAY)) {
160  offset += avctx->width * avctx->height;
161  vble_restore_plane(ctx, pic, &gb, 1, offset, width_uv, height_uv);
162 
163  offset += width_uv * height_uv;
164  vble_restore_plane(ctx, pic, &gb, 2, offset, width_uv, height_uv);
165  }
166 
167  *got_frame = 1;
168 
169  return avpkt->size;
170 }
171 
173 {
174  VBLEContext *ctx = avctx->priv_data;
175  av_freep(&ctx->val);
176 
177  return 0;
178 }
179 
181 {
182  VBLEContext *ctx = avctx->priv_data;
183 
184  /* Stash for later use */
185  ctx->avctx = avctx;
186  ff_llviddsp_init(&ctx->llviddsp);
187 
188  avctx->pix_fmt = AV_PIX_FMT_YUV420P;
189  avctx->bits_per_raw_sample = 8;
190 
191  ctx->size = av_image_get_buffer_size(avctx->pix_fmt,
192  avctx->width, avctx->height, 1);
193 
194  ctx->val = av_malloc_array(ctx->size, sizeof(*ctx->val));
195 
196  if (!ctx->val) {
197  av_log(avctx, AV_LOG_ERROR, "Could not allocate values buffer.\n");
198  return AVERROR(ENOMEM);
199  }
200 
201  return 0;
202 }
203 
205  .p.name = "vble",
206  CODEC_LONG_NAME("VBLE Lossless Codec"),
207  .p.type = AVMEDIA_TYPE_VIDEO,
208  .p.id = AV_CODEC_ID_VBLE,
209  .priv_data_size = sizeof(VBLEContext),
211  .close = vble_decode_close,
213  .p.capabilities = AV_CODEC_CAP_DR1 | AV_CODEC_CAP_FRAME_THREADS,
214 };
AV_LOG_WARNING
#define AV_LOG_WARNING
Something somehow does not look correct.
Definition: log.h:186
get_bits_left
static int get_bits_left(GetBitContext *gb)
Definition: get_bits.h:694
AVERROR
Filter the word “frame” indicates either a video frame or a group of audio as stored in an AVFrame structure Format for each input and each output the list of supported formats For video that means pixel format For audio that means channel sample they are references to shared objects When the negotiation mechanism computes the intersection of the formats supported at each end of a all references to both lists are replaced with a reference to the intersection And when a single format is eventually chosen for a link amongst the remaining all references to the list are updated That means that if a filter requires that its input and output have the same format amongst a supported all it has to do is use a reference to the same list of formats query_formats can leave some formats unset and return AVERROR(EAGAIN) to cause the negotiation mechanism toagain later. That can be used by filters with complex requirements to use the format negotiated on one link to set the formats supported on another. Frame references ownership and permissions
vble_decode_close
static av_cold int vble_decode_close(AVCodecContext *avctx)
Definition: vble.c:172
VBLEContext::llviddsp
LLVidDSPContext llviddsp
Definition: vble.c:39
vble_decode_init
static av_cold int vble_decode_init(AVCodecContext *avctx)
Definition: vble.c:180
AVFrame
This structure describes decoded (raw) audio or video data.
Definition: frame.h:340
AVPacket::data
uint8_t * data
Definition: packet.h:522
FFCodec
Definition: codec_internal.h:127
VBLEContext
Definition: vble.c:37
AVFrame::flags
int flags
Frame flags, a combination of AV_FRAME_FLAGS.
Definition: frame.h:612
init_get_bits
static int init_get_bits(GetBitContext *s, const uint8_t *buffer, int bit_size)
Initialize GetBitContext.
Definition: get_bits.h:514
thread.h
AVFrame::data
uint8_t * data[AV_NUM_DATA_POINTERS]
pointer to the picture/channel planes.
Definition: frame.h:361
ff_thread_get_buffer
the pkt_dts and pkt_pts fields in AVFrame will work as usual Restrictions on codec whose streams don t reset across will not work because their bitstreams cannot be decoded in parallel *The contents of buffers must not be read before as well as code calling up to before the decode process starts Call have so the codec calls ff_thread_report set FF_CODEC_CAP_ALLOCATE_PROGRESS in FFCodec caps_internal and use ff_thread_get_buffer() to allocate frames. Otherwise decode directly into the user-supplied frames. Call ff_thread_report_progress() after some part of the current picture has decoded. A good place to put this is where draw_horiz_band() is called - add this if it isn 't called anywhere
skip_bits
static void skip_bits(GetBitContext *s, int n)
Definition: get_bits.h:381
get_bits
static unsigned int get_bits(GetBitContext *s, int n)
Read 1-25 bits.
Definition: get_bits.h:335
FFCodec::p
AVCodec p
The public AVCodec.
Definition: codec_internal.h:131
GetBitContext
Definition: get_bits.h:108
vble_restore_plane
static void vble_restore_plane(VBLEContext *ctx, AVFrame *pic, GetBitContext *gb, int plane, int offset, int width, int height)
Definition: vble.c:85
val
static double val(void *priv, double ch)
Definition: aeval.c:78
LLVidDSPContext
Definition: lossless_videodsp.h:28
AV_LOG_ERROR
#define AV_LOG_ERROR
Something went wrong and cannot losslessly be recovered.
Definition: log.h:180
av_cold
#define av_cold
Definition: attributes.h:90
AV_FRAME_FLAG_KEY
#define AV_FRAME_FLAG_KEY
A flag to mark frames that are keyframes.
Definition: frame.h:591
width
#define width
FF_CODEC_DECODE_CB
#define FF_CODEC_DECODE_CB(func)
Definition: codec_internal.h:287
AVFormatContext::flags
int flags
Flags modifying the (de)muxer behaviour.
Definition: avformat.h:1406
AVCodecContext::bits_per_raw_sample
int bits_per_raw_sample
Bits per sample/pixel of internal libavcodec pixel/sample format.
Definition: avcodec.h:1574
ctx
AVFormatContext * ctx
Definition: movenc.c:48
get_bits.h
AV_PIX_FMT_YUV420P
@ AV_PIX_FMT_YUV420P
planar YUV 4:2:0, 12bpp, (1 Cr & Cb sample per 2x2 Y samples)
Definition: pixfmt.h:73
CODEC_LONG_NAME
#define CODEC_LONG_NAME(str)
Definition: codec_internal.h:272
AV_CODEC_CAP_FRAME_THREADS
#define AV_CODEC_CAP_FRAME_THREADS
Codec supports frame-level multithreading.
Definition: codec.h:110
VBLEContext::size
int size
Definition: vble.c:41
AV_PICTURE_TYPE_I
@ AV_PICTURE_TYPE_I
Intra.
Definition: avutil.h:279
get_bits1
static unsigned int get_bits1(GetBitContext *s)
Definition: get_bits.h:388
mathops.h
VBLEContext::avctx
AVCodecContext * avctx
Definition: vble.c:38
AVFrame::pict_type
enum AVPictureType pict_type
Picture type of the frame.
Definition: frame.h:442
init
int(* init)(AVBSFContext *ctx)
Definition: dts2pts.c:365
AV_CODEC_CAP_DR1
#define AV_CODEC_CAP_DR1
Codec uses get_buffer() or get_encode_buffer() for allocating buffers and supports custom allocators.
Definition: codec.h:52
AV_CODEC_FLAG_GRAY
#define AV_CODEC_FLAG_GRAY
Only decode/encode grayscale.
Definition: avcodec.h:322
AVPacket::size
int size
Definition: packet.h:523
LUT
Definition: vf_morpho.c:62
codec_internal.h
VBLEContext::val
uint8_t * val
This array first holds the lengths of vlc symbols and then their value.
Definition: vble.c:42
height
#define height
av_image_get_buffer_size
int av_image_get_buffer_size(enum AVPixelFormat pix_fmt, int width, int height, int align)
Return the size in bytes of the amount of data required to store an image with the given parameters.
Definition: imgutils.c:466
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
version
version
Definition: libkvazaar.c:321
vble_decode_frame
static int vble_decode_frame(AVCodecContext *avctx, AVFrame *pic, int *got_frame, AVPacket *avpkt)
Definition: vble.c:117
i
#define i(width, name, range_min, range_max)
Definition: cbs_h2645.c:255
show_bits
static unsigned int show_bits(GetBitContext *s, int n)
Show 1-25 bits.
Definition: get_bits.h:371
av_malloc_array
#define av_malloc_array(a, b)
Definition: tableprint_vlc.h:31
AVCodec::name
const char * name
Name of the codec implementation.
Definition: codec.h:194
AVCodecContext::height
int height
Definition: avcodec.h:618
AVCodecContext::pix_fmt
enum AVPixelFormat pix_fmt
Pixel format, see AV_PIX_FMT_xxx.
Definition: avcodec.h:657
avcodec.h
stride
#define stride
Definition: h264pred_template.c:537
ret
ret
Definition: filter_design.txt:187
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
AV_RL32
uint64_t_TMPL AV_WL64 unsigned int_TMPL AV_RL32
Definition: bytestream.h:92
ff_llviddsp_init
void ff_llviddsp_init(LLVidDSPContext *c)
Definition: lossless_videodsp.c:113
AVCodecContext
main external API structure.
Definition: avcodec.h:445
AVMEDIA_TYPE_VIDEO
@ AVMEDIA_TYPE_VIDEO
Definition: avutil.h:201
AV_CODEC_ID_VBLE
@ AV_CODEC_ID_VBLE
Definition: codec_id.h:207
lossless_videodsp.h
AVCodecContext::priv_data
void * priv_data
Definition: avcodec.h:472
AVPacket
This structure stores compressed data.
Definition: packet.h:499
av_freep
#define av_freep(p)
Definition: tableprint_vlc.h:34
src
INIT_CLIP pixel * src
Definition: h264pred_template.c:418
AVCodecContext::width
int width
picture width / height.
Definition: avcodec.h:618
imgutils.h
AVFrame::linesize
int linesize[AV_NUM_DATA_POINTERS]
For video, a positive or negative value, which is typically indicating the size in bytes of each pict...
Definition: frame.h:385
av_log
#define av_log(a,...)
Definition: tableprint_vlc.h:27
AVERROR_INVALIDDATA
#define AVERROR_INVALIDDATA
Invalid data found when processing input.
Definition: error.h:61
ff_vble_decoder
const FFCodec ff_vble_decoder
Definition: vble.c:204
vble_unpack
static int vble_unpack(VBLEContext *ctx, GetBitContext *gb)
Definition: vble.c:45