mirror of https://git.ffmpeg.org/ffmpeg.git
260 lines
6.9 KiB
Plaintext
260 lines
6.9 KiB
Plaintext
=============================================
|
|
SNOW Video Codec Specification Draft 20070103
|
|
=============================================
|
|
|
|
|
|
Definitions:
|
|
============
|
|
|
|
MUST the specific part must be done to conform to this standard
|
|
SHOULD it is recommended to be done that way, but not strictly required
|
|
|
|
ilog2(x) is the rounded down logarithm of x with basis 2
|
|
ilog2(0) = 0
|
|
|
|
Type definitions:
|
|
=================
|
|
|
|
b 1-bit range coded
|
|
u unsigned scalar value range coded
|
|
s signed scalar value range coded
|
|
|
|
|
|
Bitstream syntax:
|
|
=================
|
|
|
|
frame:
|
|
header
|
|
prediction
|
|
residual
|
|
|
|
header:
|
|
keyframe b MID_STATE
|
|
if(keyframe || always_reset)
|
|
reset_contexts
|
|
if(keyframe){
|
|
version u header_state
|
|
always_reset b header_state
|
|
temporal_decomposition_type u header_state
|
|
temporal_decomposition_count u header_state
|
|
spatial_decomposition_count u header_state
|
|
colorspace_type u header_state
|
|
chroma_h_shift u header_state
|
|
chroma_v_shift u header_state
|
|
spatial_scalability b header_state
|
|
max_ref_frames-1 u header_state
|
|
qlogs
|
|
}
|
|
|
|
spatial_decomposition_type s header_state
|
|
qlog s header_state
|
|
mv_scale s header_state
|
|
qbias s header_state
|
|
block_max_depth s header_state
|
|
|
|
qlogs:
|
|
for(plane=0; plane<2; plane++){
|
|
quant_table[plane][0][0] s header_state
|
|
for(level=0; level < spatial_decomposition_count; level++){
|
|
quant_table[plane][level][1]s header_state
|
|
quant_table[plane][level][3]s header_state
|
|
}
|
|
}
|
|
|
|
reset_contexts
|
|
*_state[*]= MID_STATE
|
|
|
|
prediction:
|
|
for(y=0; y<block_count_vertical; y++)
|
|
for(x=0; x<block_count_horizontal; x++)
|
|
block(0)
|
|
|
|
block(level):
|
|
if(keyframe){
|
|
intra=1
|
|
y_diff=cb_diff=cr_diff=0
|
|
}else{
|
|
if(level!=max_block_depth){
|
|
s_context= 2*left->level + 2*top->level + topleft->level + topright->level
|
|
leaf b block_state[4 + s_context]
|
|
}
|
|
if(level==max_block_depth || leaf){
|
|
intra b block_state[1 + left->intra + top->intra]
|
|
if(intra){
|
|
y_diff s block_state[32]
|
|
cb_diff s block_state[64]
|
|
cr_diff s block_state[96]
|
|
}else{
|
|
ref_context= ilog2(2*left->ref) + ilog2(2*top->ref)
|
|
if(ref_frames > 1)
|
|
ref u block_state[128 + 1024 + 32*ref_context]
|
|
mx_context= ilog2(2*abs(left->mx - top->mx))
|
|
my_context= ilog2(2*abs(left->my - top->my))
|
|
mvx_diff s block_state[128 + 32*(mx_context + 16*!!ref)]
|
|
mvy_diff s block_state[128 + 32*(my_context + 16*!!ref)]
|
|
}
|
|
}else{
|
|
block(level+1)
|
|
block(level+1)
|
|
block(level+1)
|
|
block(level+1)
|
|
}
|
|
}
|
|
|
|
|
|
residual:
|
|
FIXME
|
|
|
|
|
|
|
|
Tag description:
|
|
----------------
|
|
|
|
version
|
|
0
|
|
this MUST NOT change within a bitstream
|
|
|
|
always_reset
|
|
if 1 then the range coder contexts will be reset after each frame
|
|
|
|
temporal_decomposition_type
|
|
0
|
|
|
|
temporal_decomposition_count
|
|
0
|
|
|
|
spatial_decomposition_count
|
|
FIXME
|
|
|
|
colorspace_type
|
|
0
|
|
this MUST NOT change within a bitstream
|
|
|
|
chroma_h_shift
|
|
log2(luma.width / chroma.width)
|
|
this MUST NOT change within a bitstream
|
|
|
|
chroma_v_shift
|
|
log2(luma.height / chroma.height)
|
|
this MUST NOT change within a bitstream
|
|
|
|
spatial_scalability
|
|
0
|
|
|
|
max_ref_frames
|
|
maximum number of reference frames
|
|
this MUST NOT change within a bitstream
|
|
|
|
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=1
|
|
|
|
spatial_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 || keyframe
|
|
|
|
qlog
|
|
quality (logarthmic quantizer scale)
|
|
stored as delta from last, last is reset to 0 if always_reset || keyframe
|
|
|
|
mv_scale
|
|
stored as delta from last, last is reset to 0 if always_reset || keyframe
|
|
FIXME check that everything works fine if this chanes between frames
|
|
|
|
qbias
|
|
dequantization bias
|
|
stored as delta from last, last is reset to 0 if always_reset || keyframe
|
|
|
|
block_max_depth
|
|
maximum depth of the block tree
|
|
stored as delta from last, last is reset to 0 if always_reset || keyframe
|
|
|
|
quant_table
|
|
quantiztation table
|
|
|
|
Range Coder:
|
|
============
|
|
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 its outside of the image in
|
|
which case it is set to the left block
|
|
|
|
if this block has no larger parent block or its 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)>>8
|
|
|
|
2. the median of the scaled left, top and top-right vectors is used as
|
|
motion vector prediction
|
|
|
|
3. the used motion vector is the sum of the predictor and
|
|
(mvx_diff, mvy_diff)*mv_scale
|
|
|
|
|
|
Intra DC Predicton:
|
|
======================
|
|
the luma and chroma values of the left block are used as predictors
|
|
|
|
the used luma and chroma is the sum of the predictor and y_diff, cb_diff, cr_diff
|
|
|
|
|
|
Motion Compensation:
|
|
====================
|
|
FIXME
|
|
|
|
LL band prediction:
|
|
===================
|
|
FIXME
|
|
|
|
Dequantizaton:
|
|
==============
|
|
FIXME
|
|
|
|
Wavelet Transform:
|
|
==================
|
|
FIXME
|
|
|
|
TODO:
|
|
=====
|
|
Important:
|
|
finetune initial contexts
|
|
spatial_decomposition_count per frame?
|
|
flip wavelet?
|
|
try to use the wavelet transformed predicted image (motion compensated image) as context for coding the residual coefficients
|
|
try the MV length as context for coding the residual coefficients
|
|
use extradata for stuff which is in the keyframes now?
|
|
the MV median predictor is patented IIRC
|
|
|
|
Not Important:
|
|
spatial_scalability b vs u (!= 0 breaks syntax anyway so we can add a u later)
|
|
|
|
|
|
Credits:
|
|
========
|
|
Michael Niedermayer
|
|
Loren Merritt
|
|
|
|
|
|
Copyright:
|
|
==========
|
|
GPL + GFDL + whatever is needed to make this a RFC
|