Re: [FFmpeg-devel] [PATCH v7 3/4] avcodec/hevc: Add alpha layer support

[James Almer <jamrial@gmail.com>]

[-- Attachment #1.1.1: Type: text/plain, Size: 9497 bytes --]

On 2/11/2025 12:57 PM, Zhao Zhili wrote:
> 
> 
>> On Feb 11, 2025, at 23:37, Andreas Rheinhardt <andreas.rheinhardt@outlook.com> wrote:
>>
>> Zhao Zhili:
>>> From: Zhao Zhili <zhilizhao@tencent.com>
>>>
>>> Signed-off-by: Zhao Zhili <zhilizhao@tencent.com>
>>> ---
>>> libavcodec/hevc/hevcdec.c | 73 ++++++++++++++++++++++++++++++++++++++-
>>> libavcodec/hevc/hevcdec.h |  2 ++
>>> libavcodec/hevc/refs.c    | 35 ++++++++++++++++++-
>>> 3 files changed, 108 insertions(+), 2 deletions(-)
>>>
>>> diff --git a/libavcodec/hevc/hevcdec.c b/libavcodec/hevc/hevcdec.c
>>> index e9c045f7a1..f71edf213b 100644
>>> --- a/libavcodec/hevc/hevcdec.c
>>> +++ b/libavcodec/hevc/hevcdec.c
>>> @@ -466,6 +466,25 @@ static int export_multilayer(HEVCContext *s, const HEVCVPS *vps)
>>>      return 0;
>>> }
>>>
>>> +int ff_hevc_is_alpha_video(const HEVCContext *s)
>>> +{
>>> +    const HEVCVPS *vps = s->vps;
>>> +    int ret = 0;
>>> +
>>> +    if (vps->nb_layers != 2 || !vps->layer_id_in_nuh[1])
>>> +        return 0;
>>> +
>>> +    /* decode_vps_ext() guarantees that SCALABILITY_AUXILIARY with AuxId other
>>> +     * than alpha cannot reach here.
>>> +     */
>>> +    ret = (s->vps->scalability_mask_flag & HEVC_SCALABILITY_AUXILIARY);
>>> +
>>> +    av_log(s->avctx, AV_LOG_DEBUG, "Multi layer video, %s alpha video\n",
>>> +           ret ? "is" : "not");
>>> +
>>> +    return ret;
>>> +}
>>> +
>>> static int setup_multilayer(HEVCContext *s, const HEVCVPS *vps)
>>> {
>>>      unsigned layers_active_output = 0, highest_layer;
>>> @@ -473,6 +492,18 @@ static int setup_multilayer(HEVCContext *s, const HEVCVPS *vps)
>>>      s->layers_active_output = 1;
>>>      s->layers_active_decode = 1;
>>>
>>> +    if (ff_hevc_is_alpha_video(s)) {
>>> +        const AVPixFmtDescriptor *desc = av_pix_fmt_desc_get(s->avctx->pix_fmt);
>>> +
>>> +        if (!(desc->flags & AV_PIX_FMT_FLAG_ALPHA))
>>> +            return 0;
>>> +
>>> +        s->layers_active_decode = (1 << vps->nb_layers) - 1;
>>> +        s->layers_active_output = 1;
>>> +
>>> +        return 0;
>>> +    }
>>> +
>>>      // nothing requested - decode base layer only
>>>      if (!s->nb_view_ids)
>>>          return 0;
>>> @@ -530,6 +561,34 @@ static int setup_multilayer(HEVCContext *s, const HEVCVPS *vps)
>>>      return 0;
>>> }
>>>
>>> +static enum AVPixelFormat map_to_alpha_format(HEVCContext *s,
>>> +                                              enum AVPixelFormat pix_fmt)
>>> +{
>>> +    switch (pix_fmt) {
>>> +    case AV_PIX_FMT_YUV420P:
>>> +    case AV_PIX_FMT_YUVJ420P:
>>> +        return AV_PIX_FMT_YUVA420P;
>>> +    case AV_PIX_FMT_YUV420P10:
>>> +        return AV_PIX_FMT_YUVA420P10;
>>> +    case AV_PIX_FMT_YUV444P:
>>> +        return AV_PIX_FMT_YUVA444P;
>>> +    case AV_PIX_FMT_YUV422P:
>>> +        return AV_PIX_FMT_YUVA422P;
>>> +    case AV_PIX_FMT_YUV422P10LE:
>>> +        return AV_PIX_FMT_YUVA422P10LE;
>>> +    case AV_PIX_FMT_YUV444P10:
>>> +        return AV_PIX_FMT_YUVA444P10;
>>> +    case AV_PIX_FMT_YUV444P12:
>>> +        return AV_PIX_FMT_YUVA444P12;
>>> +    case AV_PIX_FMT_YUV422P12:
>>> +        return AV_PIX_FMT_YUVA422P12;
>>> +    default:
>>> +        av_log(s->avctx, AV_LOG_WARNING, "No alpha pixel format map for %s\n",
>>> +               av_get_pix_fmt_name(pix_fmt));
>>> +        return AV_PIX_FMT_NONE;
>>> +    }
>>> +}
>>> +
>>> static enum AVPixelFormat get_format(HEVCContext *s, const HEVCSPS *sps)
>>> {
>>> #define HWACCEL_MAX (CONFIG_HEVC_DXVA2_HWACCEL + \
>>> @@ -540,9 +599,13 @@ static enum AVPixelFormat get_format(HEVCContext *s, const HEVCSPS *sps)
>>>                       CONFIG_HEVC_VIDEOTOOLBOX_HWACCEL + \
>>>                       CONFIG_HEVC_VDPAU_HWACCEL + \
>>>                       CONFIG_HEVC_VULKAN_HWACCEL)
>>> -    enum AVPixelFormat pix_fmts[HWACCEL_MAX + 2], *fmt = pix_fmts;
>>> +    enum AVPixelFormat pix_fmts[HWACCEL_MAX + 3], *fmt = pix_fmts;
>>> +    enum AVPixelFormat alpha_fmt = AV_PIX_FMT_NONE;
>>>      int ret;
>>>
>>> +    if (ff_hevc_is_alpha_video(s))
>>> +        alpha_fmt = map_to_alpha_format(s, sps->pix_fmt);
>>> +
>>>      switch (sps->pix_fmt) {
>>>      case AV_PIX_FMT_YUV420P:
>>>      case AV_PIX_FMT_YUVJ420P:
>>> @@ -664,6 +727,8 @@ static enum AVPixelFormat get_format(HEVCContext *s, const HEVCSPS *sps)
>>>          break;
>>>      }
>>>
>>> +    if (alpha_fmt != AV_PIX_FMT_NONE)
>>> +        *fmt++ = alpha_fmt;
>>>      *fmt++ = sps->pix_fmt;
>>>      *fmt = AV_PIX_FMT_NONE;
>>>
>>> @@ -3194,6 +3259,12 @@ static int hevc_frame_start(HEVCContext *s, HEVCLayerContext *l,
>>>                  !sps->vui.common.video_signal_type_present_flag)
>>>                  pix_fmt = sps_base->pix_fmt;
>>>
>>> +            // Ignore range mismatch between base layer and alpha layer
>>> +            if (ff_hevc_is_alpha_video(s) &&
>>> +                sps_base->pix_fmt == AV_PIX_FMT_YUV420P &&
>>> +                pix_fmt == AV_PIX_FMT_YUVJ420P)
>>> +                pix_fmt = sps_base->pix_fmt;
>>> +
>>>              if (pix_fmt     != sps_base->pix_fmt ||
>>>                  sps->width  != sps_base->width   ||
>>>                  sps->height != sps_base->height) {
>>> diff --git a/libavcodec/hevc/hevcdec.h b/libavcodec/hevc/hevcdec.h
>>> index 4e95035688..b2b725b5cd 100644
>>> --- a/libavcodec/hevc/hevcdec.h
>>> +++ b/libavcodec/hevc/hevcdec.h
>>> @@ -714,6 +714,8 @@ void ff_hevc_hls_residual_coding(HEVCLocalContext *lc, const HEVCPPS *pps,
>>>
>>> void ff_hevc_hls_mvd_coding(HEVCLocalContext *lc, int x0, int y0, int log2_cb_size);
>>>
>>> +int ff_hevc_is_alpha_video(const HEVCContext *s);
>>> +
>>> extern const uint8_t ff_hevc_qpel_extra_before[4];
>>> extern const uint8_t ff_hevc_qpel_extra_after[4];
>>> extern const uint8_t ff_hevc_qpel_extra[4];
>>> diff --git a/libavcodec/hevc/refs.c b/libavcodec/hevc/refs.c
>>> index dd7f7f95a8..6f10efd0ac 100644
>>> --- a/libavcodec/hevc/refs.c
>>> +++ b/libavcodec/hevc/refs.c
>>> @@ -79,6 +79,31 @@ void ff_hevc_flush_dpb(HEVCContext *s)
>>>      }
>>> }
>>>
>>> +static int replace_alpha_plane(AVFrame *alpha, AVFrame *base)
>>> +{
>>> +    AVBufferRef *base_a = av_frame_get_plane_buffer(base, 3);
>>> +    uintptr_t data = (uintptr_t)alpha->data[0];
>>> +    int ret;
>>> +
>>> +    for (int i = 0; i < FF_ARRAY_ELEMS(alpha->buf) && alpha->buf[i]; i++) {
>>> +        AVBufferRef *buf = alpha->buf[i];
>>> +        uintptr_t buf_begin = (uintptr_t)buf->data;
>>> +
>>> +        if (data >=  buf_begin && data < buf_begin + buf->size) {
>>> +            ret = av_buffer_replace(&alpha->buf[i], base_a);
>>> +            if (ret < 0)
>>> +                return ret;
>>> +
>>> +            alpha->linesize[0] = base->linesize[3];
>>> +            alpha->data[0] = base->data[3];
>>> +
>>> +            return 0;
>>> +        }
>>> +    }
>>
>> Why does the decoding process actually need multiple references to the
>> buffer of the alpha plane?
> 
> I’m not sure if I understand your question correctly.
> 
> 1. Both the base layer and the alpha layer are decoded as yuv420p.
> 2. The y plane of alpha layer is actually alpha.
> 3. The decoder finally output yuva, not two yuv420p.
> 
> So here make y plane of alpha frame reference the alpha plane of base frame.
> When output, the base frame will contain YUV and alpha from two layers.

The loop makes it look like you're potentially creating references to 
base_a in all buf[] entries from alpha, when all you need is one in 
alpha->buf[0], right?

> 
>>
>>> +
>>> +    return AVERROR_BUG;
>>> +}
>>> +
>>> static HEVCFrame *alloc_frame(HEVCContext *s, HEVCLayerContext *l)
>>> {
>>>      const HEVCVPS *vps = l->sps->vps;
>>> @@ -103,7 +128,7 @@ static HEVCFrame *alloc_frame(HEVCContext *s, HEVCLayerContext *l)
>>>          }
>>>
>>>          // add view ID side data if it's nontrivial
>>> -        if (vps->nb_layers > 1 || view_id) {
>>> +        if (!ff_hevc_is_alpha_video(s) && (vps->nb_layers > 1 || view_id)) {
>>>              HEVCSEITDRDI *tdrdi = &s->sei.tdrdi;
>>>              AVFrameSideData *sd = av_frame_side_data_new(&frame->f->side_data,
>>>                                                           &frame->f->nb_side_data,
>>> @@ -161,7 +186,15 @@ static HEVCFrame *alloc_frame(HEVCContext *s, HEVCLayerContext *l)
>>>          if (ret < 0)
>>>              goto fail;
>>>
>>> +
>>>          frame->pps = av_refstruct_ref_c(s->pps);
>>> +        if (l != &s->layers[0] && ff_hevc_is_alpha_video(s)) {
>>> +            AVFrame *alpha = frame->f;
>>> +            AVFrame *base = s->layers[0].cur_frame->f;
>>> +            ret = replace_alpha_plane(alpha, base);
>>> +            if (ret < 0)
>>> +                goto fail;
>>> +        }
>>>
>>>          return frame;
>>> fail:
>>
>> _______________________________________________
>> ffmpeg-devel mailing list
>> ffmpeg-devel@ffmpeg.org
>> https://ffmpeg.org/mailman/listinfo/ffmpeg-devel
>>
>> To unsubscribe, visit link above, or email
>> ffmpeg-devel-request@ffmpeg.org with subject "unsubscribe".
> 
> _______________________________________________
> ffmpeg-devel mailing list
> ffmpeg-devel@ffmpeg.org
> https://ffmpeg.org/mailman/listinfo/ffmpeg-devel
> 
> To unsubscribe, visit link above, or email
> ffmpeg-devel-request@ffmpeg.org with subject "unsubscribe".


[-- Attachment #1.2: OpenPGP digital signature --]
[-- Type: application/pgp-signature, Size: 495 bytes --]

[-- Attachment #2: Type: text/plain, Size: 251 bytes --]

_______________________________________________
ffmpeg-devel mailing list
ffmpeg-devel@ffmpeg.org
https://ffmpeg.org/mailman/listinfo/ffmpeg-devel

To unsubscribe, visit link above, or email
ffmpeg-devel-request@ffmpeg.org with subject "unsubscribe".