[FFmpeg-devel] [PATCH 1/6] avcodec/h266: add shared header for h266

[Mark Thompson]

On 21/12/2020 06:07, Nuo Mi wrote:
> ---
>   libavcodec/h266.h | 121 ++++++++++++++++++++++++++++++++++++++++++++++
>   1 file changed, 121 insertions(+)
>   create mode 100644 libavcodec/h266.h
> 
> diff --git a/libavcodec/h266.h b/libavcodec/h266.h
> new file mode 100644
> index 0000000000..d5793b76fc
> --- /dev/null
> +++ b/libavcodec/h266.h
> @@ -0,0 +1,121 @@
> +/*
> + * H.266 shared code
> + *
> + * 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
> + */
> +
> +#ifndef AVCODEC_H266_H
> +#define AVCODEC_H266_H
> +
> +/**
> + * Table 5 – NAL unit type codes and NAL unit type classes in
> + * T-REC-H.266-202008
> + */
> +enum H266NALUnitType {

You don't use this type name anywhere.  I don't think there is any use in including it.

> +    H266_NAL_TRAIL       = 0,

Probably clearer as H266_NAL_UNIT_TYPE_FOO or H266_NUT_FOO?

> +    H266_NAL_STSA        = 1,
> +    H266_NAL_RADL        = 2,
> +    H266_NAL_RASL        = 3,
> +    H266_NAL_RSV_VCL_4   = 4,
> +    H266_NAL_RSV_VCL_5   = 5,
> +    H266_NAL_RSV_VCL_6   = 6,
> +    H266_NAL_IDR_W_RADL  = 7,
> +    H266_NAL_IDR_N_LP    = 8,
> +    H266_NAL_CRA_NUT     = 9,
> +    H266_NAL_GDR_NUT     = 10,
> +    H266_NAL_RSV_IRAP_11 = 11,
> +    H266_NAL_OPI         = 12,
> +    H266_NAL_DCI         = 13,
> +    H266_NAL_VPS         = 14,
> +    H266_NAL_SPS         = 15,
> +    H266_NAL_PPS         = 16,
> +    H266_NAL_PREFIX_APS  = 17,
> +    H266_NAL_SUFFIX_APS  = 18,
> +    H266_NAL_PH          = 19,
> +    H266_NAL_AUD         = 20,
> +    H266_NAL_EOS_NUT     = 21,
> +    H266_NAL_EOB_NUT     = 22,

The redundant _NUT suffixes are inconsistent.

> +    H266_NAL_PREFIX_SEI  = 23,
> +    H266_NAL_SUFFIX_SEI  = 24,
> +    H266_NAL_FD_NUT      = 25,
> +    H266_NAL_RSV_NVCL_26 = 26,
> +    H266_NAL_RSV_NVCL_27 = 27,
> +    H266_NAL_UNSPEC_28   = 28,
> +    H266_NAL_UNSPEC_29   = 29,
> +    H266_NAL_UNSPEC_30   = 30,
> +    H266_NAL_UNSPEC_31   = 31,
> +};
> +
> +enum H266SliceType {

This type name too.

> +    H266_SLICE_B = 0,

H266_SLICE_TYPE_B

> +    H266_SLICE_P = 1,
> +    H266_SLICE_I = 2,
> +};
> +
> +enum {
> +    H266_MAX_PLANES = 3,
> +    //7.4.3.3 The value of vps_max_sublayers_minus1 shall be in the range of 0 to 6, inclusive
> +    H266_MAX_SUB_LAYERS = 7,
> +
> +    // 7.3.2.3: vps_video_parameter_set_id is u(4).
> +    H266_MAX_VPS_COUNT = 16,
> +    // 7.3.2.4: sps_seq_parameter_set_id is in [0, 15].

It's u(4), not a stated constraint.  (Unlike in H.264, where these ids very ue(v) with a constraint in the text.)

> +    H266_MAX_SPS_COUNT = 16,
> +    // 7.3.2.5: pps_pic_parameter_set_id is in [0, 63].

u(6)

> +    H266_MAX_PPS_COUNT = 64,
> +
> +    // A.4.2: MaxDpbSize is bounded above by 16.

The definition in terms of maxDpbPicBuf is clearer than it was in H.265, so I think say that rather than just the result.

> +    H266_MAX_DPB_SIZE = 16,
> +
> +    //7.4.3.4 sps_num_ref_pic_lists in range [0, 64]
> +    H266_MAX_REF_PIC_LISTS = 64,
> +
> +    //7.4.3.3 sps_num_points_in_qp_table_minus1[i] in range [0, 36 − sps_qp_table_start_minus26[i]],
> +    //sps_qp_table_start_minus26[i] in range [sps_qp_table_start_minus26[i] −26 − QpBdOffset, 36]
> +    //for 10 bitsQpBdOffset is 12, so sps_num_points_in_qp_table_minus1[i] in range [0, 74]
> +    H266_MAX_POINTS_IN_QP_TABLE = 75,
> +
> +    // 7.4.6.1: hrd_cpb_cnt_minus1 is in [0, 31].
> +    H266_MAX_CPB_CNT = 32,
> +
> +    // A.4.1: in table A.6 the highest level allows a MaxLumaPs of 35 651 584.

Table A.1 is the reference for MaxLumaPs.  (Table A.6 is only informative, though this value does appear for 8K.)

> +    H266_MAX_LUMA_PS = 35651584,
> +    // A.4.1: pic_width_in_luma_samples and pic_height_in_luma_samples are
> +    // constrained to be not greater than sqrt(MaxLumaPs * 8).  Hence height/
> +    // width are bounded above by sqrt(8 * 35651584) = 16888.2 samples.
> +    H266_MAX_WIDTH  = 16888,
> +    H266_MAX_HEIGHT = 16888,
> +
> +    // A.4.1: table A.1 allows at most 20 tile rows for any level.

No it doesn't?  I don't see any reference to tile rows in table A.1.

> +    H266_MAX_TILE_ROWS    = 20, > +    // A.4.1: table A.1 allows at most 20 tile columns for any level.
> +    H266_MAX_TILE_COLUMNS = 20,
> +
> +    // A.4.1 table A.1 allows at most 600 slice for any level.
> +    H266_MAX_SLICES = 600,
> +
> +    // 7.4.8: in the worst case (tiles_enabled_flag and
> +    // entropy_coding_sync_enabled_flag are both set), entry points can be
> +    // placed at the beginning of every Ctb row in every tile, giving an
> +    // upper bound of (num_tile_columns_minus1 + 1) * PicHeightInCtbsY - 1.
> +    // Only a stream with very high resolution and perverse parameters could
> +    // get near that, though, so set a lower limit here with the maximum
> +    // possible value for 8K video (at most 135 32x32 Ctb rows).

Is this text copied from H.265 still accurate?  NumEntryPoints is implicitly calculated rather than appearing in the bitstream here.

> +    H266_MAX_ENTRY_POINT_OFFSETS = H266_MAX_TILE_COLUMNS * 135,
> +};
> +
> +#endif /* AVCODEC_H266_H */
> 

- Mark