[FFmpeg-devel] [PATCH 2/2] avformat/movenc: Add loop parameter to animated AVIF

[Vignesh Venkatasubramanian]

On Thu, Jan 5, 2023 at 1:45 AM "zhilizhao(赵志立)" <quinkblack at foxmail.com> wrote:
>
>
>
> > On Jan 5, 2023, at 06:16, Vignesh Venkatasubramanian <vigneshv-at-google.com at ffmpeg.org> wrote:
> >
> > The HEIF specification permits specifying the looping behavior of
> > animated sequences by using the EditList (elst) box. The track
> > duration will be set to the total duration of all the loops (or
> > infinite) and the duration of a single loop will be set in the edit
> > list box.
> >
> > The default behavior is to loop infinitely.
> >
> > Compliance verification:
> > * This was added in libavif recently [1] and the files produced by
> >  ffmpeg after this change have EditList boxes similar to the ones
> >  produced by libavif (and avifdec is able to parse the loop count as
> >  intended).
> > * ComplianceWarden is ok with the produced files.
> > * Chrome is able to play back the produced files.
> >
> > Signed-off-by: Vignesh Venkatasubramanian <vigneshv at google.com>
> > ---
> > libavformat/movenc.c | 35 +++++++++++++++++++++++++++++++----
> > libavformat/movenc.h |  1 +
> > 2 files changed, 32 insertions(+), 4 deletions(-)
> >
> > diff --git a/libavformat/movenc.c b/libavformat/movenc.c
> > index 36c76f7f60..8d31317838 100644
> > --- a/libavformat/movenc.c
> > +++ b/libavformat/movenc.c
> > @@ -3287,7 +3287,7 @@ static int mov_write_tkhd_tag(AVIOContext *pb, MOVMuxContext *mov,
> >     int64_t duration = av_rescale_rnd(calc_pts_duration(mov, track),
> >                                       mov->movie_timescale, track->timescale,
> >                                       AV_ROUND_UP);
> > -    int version = duration < INT32_MAX ? 0 : 1;
> > +    int version;
> >     int flags   = MOV_TKHD_FLAG_IN_MOVIE;
> >     int group   = 0;
> >
> > @@ -3295,6 +3295,14 @@ static int mov_write_tkhd_tag(AVIOContext *pb, MOVMuxContext *mov,
> >     size_t display_matrix_size;
> >     int       i;
> >
> > +    if (mov->mode == MODE_AVIF)
> > +        if (!mov->avif_loop_count)
> > +            duration = INT64_MAX;
> > +        else
> > +            duration *= mov->avif_loop_count;
> > +
> > +     version = duration < INT32_MAX ? 0 : 1;
> > +
> >     if (st) {
> >         if (mov->per_stream_grouping)
> >             group = st->index;
> > @@ -3414,7 +3422,10 @@ static int mov_write_tapt_tag(AVIOContext *pb, MOVTrack *track)
> >     return update_size(pb, pos);
> > }
> >
> > -// This box seems important for the psp playback ... without it the movie seems to hang
> > +// This box is written in the following cases:
> > +//   * Seems important for the psp playback. Without it the movie seems to hang.
> > +//   * Used for specifying the looping behavior of animated AVIF (as specified
> > +//   in Section 9.6 of the HEIF specification ISO/IEC 23008-12).
> > static int mov_write_edts_tag(AVIOContext *pb, MOVMuxContext *mov,
> >                               MOVTrack *track)
> > {
> > @@ -3425,6 +3436,7 @@ static int mov_write_edts_tag(AVIOContext *pb, MOVMuxContext *mov,
> >     int entry_size, entry_count, size;
> >     int64_t delay, start_ct = track->start_cts;
> >     int64_t start_dts = track->start_dts;
> > +    int flags = 0;
> >
> >     if (track->entry) {
> >         if (start_dts != track->cluster[0].dts || start_ct != track->cluster[0].cts) {
> > @@ -3440,6 +3452,17 @@ static int mov_write_edts_tag(AVIOContext *pb, MOVMuxContext *mov,
> >
> >     delay = av_rescale_rnd(start_dts + start_ct, mov->movie_timescale,
> >                            track->timescale, AV_ROUND_DOWN);
> > +
> > +    if (mov->mode == MODE_AVIF) {
> > +        delay = 0;
> > +        // Section 9.6.3 of ISO/IEC 23008-12: flags specifies repetition of the
> > +        // edit list as follows: (flags & 1) equal to 0 specifies that the edit
> > +        // list is not repeated, while (flags & 1) equal to 1 specifies that the
> > +        // edit list is repeated.
> > +        flags = mov->avif_loop_count != 1;
> > +        start_ct = 0;
> > +    }
> > +
> >     version |= delay < INT32_MAX ? 0 : 1;
> >
> >     entry_size = (version == 1) ? 20 : 12;
> > @@ -3452,7 +3475,7 @@ static int mov_write_edts_tag(AVIOContext *pb, MOVMuxContext *mov,
> >     avio_wb32(pb, size - 8);
> >     ffio_wfourcc(pb, "elst");
> >     avio_w8(pb, version);
> > -    avio_wb24(pb, 0); /* flags */
> > +    avio_wb24(pb, flags); /* flags */
> >
> >     avio_wb32(pb, entry_count);
> >     if (delay > 0) { /* add an empty edit to delay presentation */
> > @@ -3469,7 +3492,7 @@ static int mov_write_edts_tag(AVIOContext *pb, MOVMuxContext *mov,
> >             avio_wb32(pb, -1);
> >         }
> >         avio_wb32(pb, 0x00010000);
> > -    } else {
> > +    } else if (mov->mode != MODE_AVIF) {
> >         /* Avoid accidentally ending up with start_ct = -1 which has got a
> >          * special meaning. Normally start_ct should end up positive or zero
> >          * here, but use FFMIN in case dts is a small positive integer
> > @@ -3670,6 +3693,9 @@ static int mov_write_trak_tag(AVFormatContext *s, AVIOContext *pb, MOVMuxContext
> >                    "Not writing any edit list even though one would have been required\n");
> >     }
> >
> > +    if (mov->is_animated_avif)
> > +        mov_write_edts_tag(pb, mov, track);
> > +
> >     if (track->tref_tag)
> >         mov_write_tref_tag(pb, track);
> >
> > @@ -7761,6 +7787,7 @@ static const AVCodecTag codec_f4v_tags[] = {
> >
> > static const AVOption avif_options[] = {
> >     { "movie_timescale", "set movie timescale", offsetof(MOVMuxContext, movie_timescale), AV_OPT_TYPE_INT, {.i64 = MOV_TIMESCALE}, 1, INT_MAX, AV_OPT_FLAG_ENCODING_PARAM},
> > +    { "loop", "Number of times to loop animated AVIF: 0 - infinite loop", offsetof(MOVMuxContext, avif_loop_count), AV_OPT_TYPE_INT, {.i64 = 0}, 0, INT_MAX, AV_OPT_FLAG_ENCODING_PARAM, 0 },
>
> The code treat -loop 1 means playback 1 time. It can be misleading
> to mean 2 times, playback 1 time then repeat/loop 1 time. That’s
> how ‘-stream_loop’ option works. I’m not English native speaker,
> I don’t know which one is correct. Better make the offset by 1
> clear.
>

libavif uses the term "repetitionCount" instead of "loop" to not have
this ambiguity.

The behavior of the "loop" parameter in this implementation is similar
to WebP's "loop" parameter in ffmpeg (i.e.) loop means the number of
times it will be played back (loop == 1 => 1 playback, loop == 2 => 2
playbacks and so on).

> >     { NULL },
> > };
> > static const AVCodecTag codec_avif_tags[] = {
> > diff --git a/libavformat/movenc.h b/libavformat/movenc.h
> > index c6b3313deb..e85d83abdb 100644
> > --- a/libavformat/movenc.h
> > +++ b/libavformat/movenc.h
> > @@ -249,6 +249,7 @@ typedef struct MOVMuxContext {
> >     int64_t avif_extent_pos[2];  // index 0 is YUV and 1 is Alpha.
> >     int avif_extent_length[2];   // index 0 is YUV and 1 is Alpha.
> >     int is_animated_avif;
> > +    int avif_loop_count;
> > } MOVMuxContext;
> >
> > #define FF_MOV_FLAG_RTP_HINT              (1 <<  0)
> > --
> > 2.39.0.314.g84b9a713c41-goog
> >
> > _______________________________________________
> > ffmpeg-devel mailing list
> > ffmpeg-devel at ffmpeg.org
> > https://ffmpeg.org/mailman/listinfo/ffmpeg-devel
> >
> > To unsubscribe, visit link above, or email
> > ffmpeg-devel-request at ffmpeg.org with subject "unsubscribe".
>


-- 
Vignesh